{"schema":1,"generatedAt":"2026-10-09T22:03:12Z","generator":"Equilibrium · eqbench bench export --all","spot":{"generatedAt":"2026-10-09T22:03:12Z","suite":{"id":"20261009-160813-rt-n200-s2026","name":"200 decisions · River+Turn · seed 2026","createdAt":"2026-10-09T19:08:13Z","decisions":200,"mode":"spots","format":{"id":"cash","title":"Cash game · 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"hands":null,"solves":69,"generationSeconds":12.3,"seed":"2026","streets":{"turn":99,"river":101},"types":{"firstToAct":125,"facingBet":75},"scenarios":[{"id":"btn-bb-srp","name":"BTN vs BB · single raised","summary":"BTN opens 2.5bb, BB calls.","oop":"BB","ip":"BTN","pot":5.5,"stack":97.5,"count":29},{"id":"co-bb-srp","name":"CO vs BB · single raised","summary":"CO opens 2.5bb, BB calls.","oop":"BB","ip":"CO","pot":5.5,"stack":97.5,"count":51},{"id":"utg-bb-srp","name":"UTG vs BB · single raised","summary":"UTG opens 2.5bb, BB calls.","oop":"BB","ip":"UTG","pot":5.5,"stack":97.5,"count":36},{"id":"sb-bb-srp","name":"SB vs BB · single raised","summary":"SB opens 3bb, BB calls. SB is out of position.","oop":"SB","ip":"BB","pot":6,"stack":97,"count":30},{"id":"btn-bb-3bp","name":"BB vs BTN · 3-bet pot","summary":"BTN opens 2.5bb, BB 3-bets to 11bb, BTN calls.","oop":"BB","ip":"BTN","pot":22.5,"stack":89,"count":30},{"id":"co-btn-3bp","name":"CO vs BTN · 3-bet pot","summary":"CO opens 2.5bb, BTN 3-bets to 7.5bb, CO calls.","oop":"CO","ip":"BTN","pot":16.5,"stack":92.5,"count":24}],"solver":{"algorithm":"Discounted CFR (α = 1.5, β = 0.5, γ = 3), alternating updates, exact best-response exploitability","rootStreets":["turn","river"],"betSizes":[{"root":"turn","sizes":"bets 33% and 75% pot, raise 60%","raiseLimit":1},{"root":"river","sizes":"bets 33% and 75% pot, raise 60%","raiseLimit":2}],"allinThreshold":0.67,"targetExploitabilityPctPot":0.4,"maxIterations":1000,"meanExploitabilityPctPot":0.324,"maxExploitabilityPctPot":0.399,"minEVSpreadPot":0.02,"decisionsPerSolve":3,"handsPerSolve":null,"solveSeconds":null,"solveRecords":null},"approximations":["Turn and river subgames start from the scenario's preflop ranges; the synthetic flop/turn line that sets pot and stacks does not narrow them.","Bet trees are deliberately lean (two bet sizes, one raise size, limited raises), so the equilibrium is for that abstraction.","Solves stop near the target exploitability, so EV differences below ~0.25% of the pot are treated as ties.","Spots where every action is within 2% of the pot of each other are skipped as trivial.","EV loss is measured against a GTO opponent, not against the leaks of a real one."],"scoring":{"bestTolerancePot":0.0025,"approvedFrequency":0.1,"blunderThresholdPot":0.25},"stateVersion":2,"variants":[{"id":"v2","summary":"Default: full state with derived facts (made hand, draws, pot odds, SPR) + one choice question"},{"id":"minimal","summary":"Raw facts only (cards, positions, pot/stacks/to-call, history, actions); no derived facts"},{"id":"eq","summary":"v2 + hero equity and made-hand percentile vs villain's preflop range (Monte-Carlo), equity vs needed"},{"id":"eqrange","summary":"eq, but equity vs villain's range narrowed by its actions (strength heuristic, no solver data)"},{"id":"coach","summary":"v2 state; criteria rewritten as concise GTO theory (value/bluff/bluff-catch, MDF, polarisation)"},{"id":"multi","summary":"v2 state; 3 independently answered choice questions (v2 / coach / solver phrasing), probabilities averaged"},{"id":"noul","summary":"v2 state; one noul per action ('is <action> the highest-EV action?'), P(true) normalised"},{"id":"nuts","summary":"eqrange + exact nut ranking (holdings that beat hero now) + value-extraction guidance for strong hands"},{"id":"shortstack","summary":"v2 + short-stack preflop guidance (≤25bb: limp/call, fold or shove; small raises rarely best)"},{"id":"sizing","summary":"nuts + guidance on what each bet/raise size is for (small = thin value/protection, large = polarised)"}],"exampleState":{"decision":"d004","approxInputTokens":1075,"body":{"model":"typesafe/jev-1.13","questions":{"action":{"criteria":{"allin":"All-in for 87.1 bb (a raise of 97% of the pot after calling): the hero commits the whole remaining stack, making the pot 135 bb; the villain can only call or fold. Right with the very strongest hands, or as a bluff when the villain folds often enough.","call":"Call 20.5 bb: the hero matches the villain's bet, making the pot 68.5 bb. The hero needs at least 30% equity against the villain's betting range to break even. The next board card is then dealt. Right when the hero beats enough of the villain's bluffs and thin value bets, but raising would not earn more.","fold":"Fold: the hero gives up the hand, puts in no more chips and forfeits the 47.9 bb pot. Right when the hero's hand wins too rarely against the villain's betting range to justify paying 20.5 bb (it needs 30% equity)."},"instructions":"You are advising the hero, the player whose turn it is, in the heads-up No-Limit Texas Hold'em spot described in the state. Pick the single legal action that maximises the hero's expected value against a strong, balanced, game-theory-optimal (GTO) opponent who cannot see the hero's cards. Weigh the hero's exact hand against the villain's likely range given the betting so far, blockers, pot odds, the stack-to-pot ratio and position. Bet and raise sizes are fixed; choose only among the listed actions.","type":"choice"}},"state":{"betting_by_street":[{"actions":["CO (hero) checks","BTN (villain) bets 5.5 bb (33% pot)","CO (hero) calls 5.5 bb"],"new_cards":"3d As Jc","pot_at_start_bb":16.5,"street":"flop"},{"actions":["CO (hero) checks","BTN (villain) bets 20.5 bb (75% pot)","CO (hero) to act"],"new_cards":"4s","pot_at_start_bb":27.4,"street":"turn"}],"board":{"cards":"3d As Jc 4s","cards_spelled":"Three of diamonds, Ace of spades, Jack of clubs, Four of spades","texture":"unpaired, flush draw possible, straight possible, ace-high"},"game":{"card_notation":"rank + suit: A K Q J T(10) 9-2; s spades, h hearts, d diamonds, c clubs","setup":"6-max positions, everyone else folded preflop; 100 bb starting stacks","units":"all amounts in big blinds (bb); pot includes every chip committed, including a bet being faced","variant":"No-Limit Texas Hold'em, heads-up postflop"},"hero":{"acts":"first on each street (out of position)","draws":[],"hole_cards":"Qs Qc","hole_cards_spelled":"Queen of spades and Queen of clubs","in_position":false,"made_hand":"pocket pair of queens below 1 board card rank","position":"CO","stack_bb":87.05},"legal_actions":[{"key":"fold","label":"Fold","type":"fold"},{"chips_added_bb":20.55,"key":"call","label":"Call 20.5 bb","pot_after_bb":68.5,"type":"call"},{"chips_added_bb":87.05,"key":"allin","label":"All-in 87.1 bb (97% pot)","pot_after_bb":135,"size_pct_pot":97,"type":"allin"}],"preflop":"CO opens 2.5bb, BTN 3-bets to 7.5bb, CO calls.","spot":{"amount_to_call_bb":20.55,"effective_stack_bb":66.5,"equity_needed_to_call_pct":30,"facing_bet":true,"hero_stack_bb":87.05,"pot_bb":47.95,"pot_odds":"call 20.5 bb to win a 47.9 bb pot","stack_to_pot_ratio":1.39,"street":"turn","summary":"BTN bet; CO (hero) must call 20.5 bb, fold or raise. Pot 47.9 bb.","villain_stack_bb":66.5},"villain":{"hole_cards":"unknown","in_position":true,"position":"BTN","stack_bb":66.5,"style":"strong, balanced (GTO) player"}}}}},"players":[{"key":"bestev","model":"baseline:bestEV","name":"Best-EV oracle","kind":"baseline","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"lossBB":0,"lossBBCI":0,"best":1,"approved":0.985,"blunder":0,"invalid":0},"byStreet":{"turn":{"n":99,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"lossBB":0,"lossBBCI":0,"best":1,"approved":0.9697,"blunder":0,"invalid":0},"river":{"n":101,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"lossBB":0,"lossBBCI":0,"best":1,"approved":1,"blunder":0,"invalid":0}},"byType":{"firstToAct":{"n":125,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"lossBB":0,"lossBBCI":0,"best":1,"approved":0.984,"blunder":0,"invalid":0},"facingBet":{"n":75,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"lossBB":0,"lossBBCI":0,"best":1,"approved":0.9867,"blunder":0,"invalid":0}},"updatedAt":"2026-10-09T19:08:30Z"},{"key":"gto","model":"baseline:gto","name":"GTO (sampled)","kind":"baseline","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":97.83,"scoreCI":1.52,"lossPot":0.00117,"lossPotCI":0.00067,"lossBB":0.022,"lossBBCI":0.0135,"best":0.905,"approved":0.98,"blunder":0,"invalid":0,"distN":200,"mixedPot":0.0008,"mixedPotCI":0.0003,"mixedBB":0.0185,"tv":0,"tvCI":0,"pBest":0.9293,"confidence":null},"byStreet":{"turn":{"n":99,"score":99.13,"scoreCI":0.78,"lossPot":0.00077,"lossPotCI":0.00044,"lossBB":0.0176,"lossBBCI":0.013,"best":0.899,"approved":0.9899,"blunder":0,"invalid":0,"distN":99,"mixedPot":0.00053,"mixedPotCI":0.00027,"mixedBB":0.0106,"tv":0,"tvCI":0,"pBest":0.937,"confidence":null},"river":{"n":101,"score":96.56,"scoreCI":2.9,"lossPot":0.00156,"lossPotCI":0.00126,"lossBB":0.0262,"lossBBCI":0.0235,"best":0.9109,"approved":0.9703,"blunder":0,"invalid":0,"distN":101,"mixedPot":0.00107,"mixedPotCI":0.00054,"mixedBB":0.0262,"tv":0,"tvCI":0,"pBest":0.9218,"confidence":null}},"byType":{"firstToAct":{"n":125,"score":98.42,"scoreCI":1.32,"lossPot":0.00076,"lossPotCI":0.00052,"lossBB":0.0105,"lossBBCI":0.0089,"best":0.92,"approved":0.984,"blunder":0,"invalid":0,"distN":125,"mixedPot":0.00045,"mixedPotCI":0.00018,"mixedBB":0.0095,"tv":0,"tvCI":0,"pBest":0.9435,"confidence":null},"facingBet":{"n":75,"score":96.86,"scoreCI":3.41,"lossPot":0.00186,"lossPotCI":0.00156,"lossBB":0.041,"lossBBCI":0.0324,"best":0.88,"approved":0.9733,"blunder":0,"invalid":0,"distN":75,"mixedPot":0.00139,"mixedPotCI":0.00074,"mixedBB":0.0334,"tv":0,"tvCI":0,"pBest":0.9057,"confidence":null}},"updatedAt":"2026-10-09T19:08:30Z"},{"key":"gpt-6-luna-decisions","model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","kind":"decisionModel","provider":"OpenAI","servedBy":"OpenAI","resolvedModel":"openai/gpt-6-luna-decisions-20261006","url":"https://openrouter.ai/openai/gpt-6-luna-decisions","variant":"v2","label":"openai/gpt-6-luna-decisions [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":82.37,"scoreCI":4.93,"lossPot":0.02573,"lossPotCI":0.01118,"lossBB":0.7949,"lossBBCI":0.4386,"best":0.695,"approved":0.77,"blunder":0.04,"invalid":0,"distN":200,"mixedPot":0.03796,"mixedPotCI":0.00969,"mixedBB":1.4841,"tv":0.3237,"tvCI":0.0389,"pBest":0.6606,"confidence":0.6639},"byStreet":{"turn":{"n":99,"score":86.04,"scoreCI":6.24,"lossPot":0.03248,"lossPotCI":0.01986,"lossBB":0.7563,"lossBBCI":0.5589,"best":0.7172,"approved":0.8081,"blunder":0.0505,"invalid":0,"distN":99,"mixedPot":0.04263,"mixedPotCI":0.01658,"mixedBB":0.9513,"tv":0.291,"tvCI":0.0544,"pBest":0.6876,"confidence":0.6984},"river":{"n":101,"score":78.78,"scoreCI":7.57,"lossPot":0.01912,"lossPotCI":0.01051,"lossBB":0.8328,"lossBBCI":0.6766,"best":0.6733,"approved":0.7327,"blunder":0.0297,"invalid":0,"distN":101,"mixedPot":0.03339,"mixedPotCI":0.01022,"mixedBB":2.0064,"tv":0.3558,"tvCI":0.0551,"pBest":0.6343,"confidence":0.6301}},"byType":{"firstToAct":{"n":125,"score":80.97,"scoreCI":6.51,"lossPot":0.02795,"lossPotCI":0.01507,"lossBB":0.7772,"lossBBCI":0.569,"best":0.688,"approved":0.744,"blunder":0.04,"invalid":0,"distN":125,"mixedPot":0.03722,"mixedPotCI":0.01272,"mixedBB":0.8935,"tv":0.3402,"tvCI":0.0494,"pBest":0.6434,"confidence":0.6278},"facingBet":{"n":75,"score":84.71,"scoreCI":7.43,"lossPot":0.02203,"lossPotCI":0.01617,"lossBB":0.8246,"lossBBCI":0.6892,"best":0.7067,"approved":0.8133,"blunder":0.04,"invalid":0,"distN":75,"mixedPot":0.03921,"mixedPotCI":0.0149,"mixedBB":2.4685,"tv":0.2963,"tvCI":0.0631,"pBest":0.6895,"confidence":0.724}},"latency":{"mean":0.402,"median":0.393,"p90":0.448},"cost":{"total":0.02093,"per1k":0.1046},"tokens":{"prompt":209296,"completion":0,"promptPerDecision":1046},"inputPricePerM":0.1,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:53Z"},{"key":"jev-1.13","model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","kind":"decisionModel","provider":"TypeSafe","servedBy":"TypeSafe","resolvedModel":"typesafe/jev-1.13-20260917","url":"https://openrouter.ai/typesafe/jev-1.13","variant":"v2","label":"typesafe/jev-1.13 [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":78.57,"scoreCI":5.4,"lossPot":0.02655,"lossPotCI":0.00987,"lossBB":0.6901,"lossBBCI":0.3309,"best":0.69,"approved":0.735,"blunder":0.025,"invalid":0,"distN":200,"mixedPot":0.05237,"mixedPotCI":0.00695,"mixedBB":1.4083,"tv":0.4289,"tvCI":0.0293,"pBest":0.5354,"confidence":0.3913},"byStreet":{"turn":{"n":99,"score":82.75,"scoreCI":6.99,"lossPot":0.03179,"lossPotCI":0.0173,"lossBB":0.7976,"lossBBCI":0.5728,"best":0.7273,"approved":0.7576,"blunder":0.0404,"invalid":0,"distN":99,"mixedPot":0.06367,"mixedPotCI":0.01156,"mixedBB":1.2966,"tv":0.4287,"tvCI":0.0398,"pBest":0.5532,"confidence":0.3697},"river":{"n":101,"score":74.48,"scoreCI":8.16,"lossPot":0.02142,"lossPotCI":0.00973,"lossBB":0.5847,"lossBBCI":0.3399,"best":0.6535,"approved":0.7129,"blunder":0.0099,"invalid":0,"distN":101,"mixedPot":0.0413,"mixedPotCI":0.00725,"mixedBB":1.5178,"tv":0.4292,"tvCI":0.0432,"pBest":0.5179,"confidence":0.4126}},"byType":{"firstToAct":{"n":125,"score":72.97,"scoreCI":7.38,"lossPot":0.03337,"lossPotCI":0.01311,"lossBB":0.7305,"lossBBCI":0.3711,"best":0.648,"approved":0.648,"blunder":0.024,"invalid":0,"distN":125,"mixedPot":0.0545,"mixedPotCI":0.00908,"mixedBB":1.0575,"tv":0.4872,"tvCI":0.0344,"pBest":0.4986,"confidence":0.3273},"facingBet":{"n":75,"score":87.91,"scoreCI":7.04,"lossPot":0.01519,"lossPotCI":0.01443,"lossBB":0.6226,"lossBBCI":0.6327,"best":0.76,"approved":0.88,"blunder":0.0267,"invalid":0,"distN":75,"mixedPot":0.04883,"mixedPotCI":0.01074,"mixedBB":1.9931,"tv":0.3318,"tvCI":0.0456,"pBest":0.5967,"confidence":0.4981}},"latency":{"mean":0.454,"median":0.422,"p90":0.488},"cost":{"total":0.012737,"per1k":0.0637},"tokens":{"prompt":303262,"completion":9753,"promptPerDecision":1516},"inputPricePerM":0.042,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:52Z"},{"key":"mercury-decide","model":"inception/mercury-decide","name":"Inception Mercury Decide","kind":"decisionModel","provider":"Inception","servedBy":"Inception","resolvedModel":"inception/mercury-decide-20260930","url":"https://openrouter.ai/inception/mercury-decide","variant":"v2","label":"inception/mercury-decide [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":75.28,"scoreCI":5.27,"lossPot":0.03243,"lossPotCI":0.00994,"lossBB":0.7924,"lossBBCI":0.4237,"best":0.56,"approved":0.61,"blunder":0.01,"invalid":0,"distN":200,"mixedPot":0.04161,"mixedPotCI":0.00725,"mixedBB":1.022,"tv":0.4627,"tvCI":0.0423,"pBest":0.5225,"confidence":0.5962},"byStreet":{"turn":{"n":99,"score":76.97,"scoreCI":7.55,"lossPot":0.03955,"lossPotCI":0.01783,"lossBB":0.6383,"lossBBCI":0.3415,"best":0.5859,"approved":0.6263,"blunder":0.0202,"invalid":0,"distN":99,"mixedPot":0.05265,"mixedPotCI":0.01254,"mixedBB":0.9369,"tv":0.4669,"tvCI":0.0632,"pBest":0.5395,"confidence":0.6549},"river":{"n":101,"score":73.61,"scoreCI":7.38,"lossPot":0.02546,"lossPotCI":0.00897,"lossBB":0.9433,"lossBBCI":0.7705,"best":0.5347,"approved":0.5941,"blunder":0,"invalid":0,"distN":101,"mixedPot":0.03079,"mixedPotCI":0.00686,"mixedBB":1.1055,"tv":0.4586,"tvCI":0.0566,"pBest":0.5059,"confidence":0.5386}},"byType":{"firstToAct":{"n":125,"score":67.45,"scoreCI":7.06,"lossPot":0.04482,"lossPotCI":0.0145,"lossBB":0.832,"lossBBCI":0.3533,"best":0.464,"approved":0.456,"blunder":0.016,"invalid":0,"distN":125,"mixedPot":0.04999,"mixedPotCI":0.00988,"mixedBB":0.9422,"tv":0.5631,"tvCI":0.0486,"pBest":0.4512,"confidence":0.5256},"facingBet":{"n":75,"score":88.32,"scoreCI":6.75,"lossPot":0.01179,"lossPotCI":0.00931,"lossBB":0.7263,"lossBBCI":0.9687,"best":0.72,"approved":0.8667,"blunder":0,"invalid":0,"distN":75,"mixedPot":0.02765,"mixedPotCI":0.00939,"mixedBB":1.155,"tv":0.2953,"tvCI":0.0623,"pBest":0.6413,"confidence":0.7139}},"latency":{"mean":0.634,"median":0.572,"p90":0.833},"cost":{"total":0.004503,"per1k":0.0225},"tokens":{"prompt":225149,"completion":200,"promptPerDecision":1126},"inputPricePerM":0.02,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:53Z"},{"key":"d1","model":"liquid/d1","name":"Liquid d1","kind":"decisionModel","provider":"Liquid AI","servedBy":"Liquid","resolvedModel":"liquid/d1-20260930","url":"https://openrouter.ai/liquid/d1","variant":"v2","label":"liquid/d1 [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":74.47,"scoreCI":5.89,"lossPot":0.02702,"lossPotCI":0.00791,"lossBB":0.5563,"lossBBCI":0.2002,"best":0.65,"approved":0.715,"blunder":0.01,"invalid":0,"distN":200,"mixedPot":0.04211,"mixedPotCI":0.00682,"mixedBB":1.1274,"tv":0.3941,"tvCI":0.0403,"pBest":0.5785,"confidence":0.6134},"byStreet":{"turn":{"n":99,"score":79.76,"scoreCI":7.76,"lossPot":0.02712,"lossPotCI":0.01211,"lossBB":0.4453,"lossBBCI":0.216,"best":0.6869,"approved":0.7576,"blunder":0.0101,"invalid":0,"distN":99,"mixedPot":0.04754,"mixedPotCI":0.00952,"mixedBB":1.0061,"tv":0.3745,"tvCI":0.0547,"pBest":0.6115,"confidence":0.6058},"river":{"n":101,"score":69.28,"scoreCI":8.76,"lossPot":0.02693,"lossPotCI":0.01028,"lossBB":0.6652,"lossBBCI":0.3348,"best":0.6139,"approved":0.6733,"blunder":0.0099,"invalid":0,"distN":101,"mixedPot":0.0368,"mixedPotCI":0.0097,"mixedBB":1.2463,"tv":0.4133,"tvCI":0.0592,"pBest":0.5461,"confidence":0.6209}},"byType":{"firstToAct":{"n":125,"score":71.49,"scoreCI":7.78,"lossPot":0.03004,"lossPotCI":0.01064,"lossBB":0.5534,"lossBBCI":0.2713,"best":0.68,"approved":0.696,"blunder":0.008,"invalid":0,"distN":125,"mixedPot":0.04118,"mixedPotCI":0.0076,"mixedBB":0.8293,"tv":0.391,"tvCI":0.0536,"pBest":0.6033,"confidence":0.6277},"facingBet":{"n":75,"score":79.43,"scoreCI":8.79,"lossPot":0.02199,"lossPotCI":0.01142,"lossBB":0.5613,"lossBBCI":0.286,"best":0.6,"approved":0.7467,"blunder":0.0133,"invalid":0,"distN":75,"mixedPot":0.04366,"mixedPotCI":0.01312,"mixedBB":1.6243,"tv":0.3992,"tvCI":0.0603,"pBest":0.537,"confidence":0.5896}},"latency":{"mean":0.447,"median":0.424,"p90":0.502},"cost":{"total":0.009947,"per1k":0.0497},"tokens":{"prompt":248679,"completion":0,"promptPerDecision":1243},"inputPricePerM":0.04,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:52Z"},{"key":"clef","model":"cloudflare/clef","name":"Cloudflare Clef","kind":"decisionModel","provider":"Cloudflare","servedBy":"Cloudflare","resolvedModel":"cloudflare/clef","url":"https://openrouter.ai/cloudflare/clef","variant":"v2","label":"cloudflare/clef [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":74.38,"scoreCI":5.73,"lossPot":0.03464,"lossPotCI":0.01048,"lossBB":1.1085,"lossBBCI":0.5127,"best":0.635,"approved":0.69,"blunder":0.025,"invalid":0,"distN":200,"mixedPot":0.06992,"mixedPotCI":0.00877,"mixedBB":1.9145,"tv":0.495,"tvCI":0.0218,"pBest":0.4683,"confidence":0.2279},"byStreet":{"turn":{"n":99,"score":77.38,"scoreCI":7.59,"lossPot":0.04414,"lossPotCI":0.01803,"lossBB":1.2312,"lossBBCI":0.6709,"best":0.6364,"approved":0.6869,"blunder":0.0404,"invalid":0,"distN":99,"mixedPot":0.08836,"mixedPotCI":0.01445,"mixedBB":1.7333,"tv":0.5109,"tvCI":0.03,"pBest":0.4738,"confidence":0.212},"river":{"n":101,"score":71.43,"scoreCI":8.56,"lossPot":0.02532,"lossPotCI":0.01066,"lossBB":0.9882,"lossBBCI":0.776,"best":0.6337,"approved":0.6931,"blunder":0.0099,"invalid":0,"distN":101,"mixedPot":0.05184,"mixedPotCI":0.00877,"mixedBB":2.0921,"tv":0.4795,"tvCI":0.0315,"pBest":0.4629,"confidence":0.2434}},"byType":{"firstToAct":{"n":125,"score":71.79,"scoreCI":7.64,"lossPot":0.02989,"lossPotCI":0.01061,"lossBB":0.6409,"lossBBCI":0.2915,"best":0.648,"approved":0.656,"blunder":0.008,"invalid":0,"distN":125,"mixedPot":0.06356,"mixedPotCI":0.00997,"mixedBB":1.1767,"tv":0.5303,"tvCI":0.0235,"pBest":0.453,"confidence":0.193},"facingBet":{"n":75,"score":78.68,"scoreCI":8.41,"lossPot":0.04254,"lossPotCI":0.02163,"lossBB":1.8877,"lossBBCI":1.2637,"best":0.6133,"approved":0.7467,"blunder":0.0533,"invalid":0,"distN":75,"mixedPot":0.08052,"mixedPotCI":0.01626,"mixedBB":3.1442,"tv":0.4363,"tvCI":0.0398,"pBest":0.4937,"confidence":0.286}},"latency":{"mean":0.696,"median":0.542,"p90":1.248},"cost":{"total":0.011418,"per1k":0.0571},"tokens":{"prompt":220603,"completion":0,"promptPerDecision":1103},"inputPricePerM":0.0518,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:52Z"},{"key":"callingstation","model":"baseline:callingStation","name":"Calling station","kind":"baseline","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":73.78,"scoreCI":5.75,"lossPot":0.06643,"lossPotCI":0.02123,"lossBB":1.8025,"lossBBCI":0.7022,"best":0.635,"approved":0.705,"blunder":0.105,"invalid":0},"byStreet":{"turn":{"n":99,"score":74.25,"scoreCI":8.09,"lossPot":0.09448,"lossPotCI":0.03759,"lossBB":2.0589,"lossBBCI":0.9097,"best":0.6364,"approved":0.7172,"blunder":0.1515,"invalid":0},"river":{"n":101,"score":73.32,"scoreCI":8.2,"lossPot":0.03894,"lossPotCI":0.01899,"lossBB":1.5512,"lossBBCI":1.0692,"best":0.6337,"approved":0.6931,"blunder":0.0594,"invalid":0}},"byType":{"firstToAct":{"n":125,"score":76.77,"scoreCI":7.26,"lossPot":0.06026,"lossPotCI":0.02832,"lossBB":1.3905,"lossBBCI":0.7935,"best":0.72,"approved":0.752,"blunder":0.096,"invalid":0},"facingBet":{"n":75,"score":68.8,"scoreCI":9.37,"lossPot":0.07671,"lossPotCI":0.03137,"lossBB":2.4891,"lossBBCI":1.3185,"best":0.4933,"approved":0.6267,"blunder":0.12,"invalid":0}},"updatedAt":"2026-10-09T19:08:30Z"},{"key":"pplx-decider-v1.1-27b","model":"perplexity/pplx-decider-v1.1-27b","name":"Perplexity Decider v1.1 27B","kind":"decisionModel","provider":"Perplexity","servedBy":"Perplexity","resolvedModel":"perplexity/pplx-decider-v1.1-27b-20261006","url":"https://openrouter.ai/perplexity/pplx-decider-v1.1-27b","variant":"v2","label":"perplexity/pplx-decider-v1.1-27b [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":70.47,"scoreCI":6.06,"lossPot":0.03521,"lossPotCI":0.00931,"lossBB":0.6371,"lossBBCI":0.2027,"best":0.58,"approved":0.655,"blunder":0.015,"invalid":0,"distN":200,"mixedPot":0.04889,"mixedPotCI":0.00699,"mixedBB":1.1372,"tv":0.4603,"tvCI":0.0365,"pBest":0.512,"confidence":0.4746},"byStreet":{"turn":{"n":99,"score":75.34,"scoreCI":8.09,"lossPot":0.04095,"lossPotCI":0.0154,"lossBB":0.5134,"lossBBCI":0.202,"best":0.6162,"approved":0.6869,"blunder":0.0202,"invalid":0,"distN":99,"mixedPot":0.05922,"mixedPotCI":0.01081,"mixedBB":1.0385,"tv":0.4629,"tvCI":0.0532,"pBest":0.5366,"confidence":0.4715},"river":{"n":101,"score":65.71,"scoreCI":8.93,"lossPot":0.02958,"lossPotCI":0.01055,"lossBB":0.7583,"lossBBCI":0.3486,"best":0.5446,"approved":0.6238,"blunder":0.0099,"invalid":0,"distN":101,"mixedPot":0.03876,"mixedPotCI":0.00851,"mixedBB":1.234,"tv":0.4577,"tvCI":0.0503,"pBest":0.488,"confidence":0.4776}},"byType":{"firstToAct":{"n":125,"score":60.25,"scoreCI":8.35,"lossPot":0.0469,"lossPotCI":0.01318,"lossBB":0.7864,"lossBBCI":0.2872,"best":0.56,"approved":0.576,"blunder":0.016,"invalid":0,"distN":125,"mixedPot":0.05226,"mixedPotCI":0.0084,"mixedBB":0.9475,"tv":0.507,"tvCI":0.0482,"pBest":0.4888,"confidence":0.4549},"facingBet":{"n":75,"score":87.51,"scoreCI":6.66,"lossPot":0.01573,"lossPotCI":0.01024,"lossBB":0.3882,"lossBBCI":0.2431,"best":0.6133,"approved":0.7867,"blunder":0.0133,"invalid":0,"distN":75,"mixedPot":0.04326,"mixedPotCI":0.01229,"mixedBB":1.4534,"tv":0.3825,"tvCI":0.0507,"pBest":0.5507,"confidence":0.5074}},"latency":{"mean":0.457,"median":0.443,"p90":0.488},"cost":{"total":0.004684,"per1k":0.0234},"tokens":{"prompt":234186,"completion":200,"promptPerDecision":1171},"inputPricePerM":0.02,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:53Z"},{"key":"solar-decide","model":"upstage/solar-decide","name":"Upstage Solar Decide","kind":"decisionModel","provider":"Upstage","servedBy":"Upstage","resolvedModel":"upstage/solar-decide-20260928","url":"https://openrouter.ai/upstage/solar-decide","variant":"v2","label":"upstage/solar-decide [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":67.89,"scoreCI":5.9,"lossPot":0.05927,"lossPotCI":0.01718,"lossBB":1.4324,"lossBBCI":0.5221,"best":0.475,"approved":0.52,"blunder":0.07,"invalid":0,"distN":200,"mixedPot":0.08029,"mixedPotCI":0.01397,"mixedBB":2.617,"tv":0.5427,"tvCI":0.0325,"pBest":0.4294,"confidence":0.2118},"byStreet":{"turn":{"n":99,"score":66.33,"scoreCI":8.66,"lossPot":0.0877,"lossPotCI":0.03144,"lossBB":1.8394,"lossBBCI":0.7154,"best":0.4848,"approved":0.5152,"blunder":0.1313,"invalid":0,"distN":99,"mixedPot":0.10302,"mixedPotCI":0.02281,"mixedBB":2.0186,"tv":0.5363,"tvCI":0.0476,"pBest":0.4485,"confidence":0.2057},"river":{"n":101,"score":69.42,"scoreCI":8.05,"lossPot":0.03141,"lossPotCI":0.01236,"lossBB":1.0335,"lossBBCI":0.7552,"best":0.4653,"approved":0.5248,"blunder":0.0099,"invalid":0,"distN":101,"mixedPot":0.058,"mixedPotCI":0.0152,"mixedBB":3.2035,"tv":0.549,"tvCI":0.0444,"pBest":0.4107,"confidence":0.2177}},"byType":{"firstToAct":{"n":125,"score":75.44,"scoreCI":6.85,"lossPot":0.04223,"lossPotCI":0.02048,"lossBB":0.6622,"lossBBCI":0.336,"best":0.592,"approved":0.616,"blunder":0.048,"invalid":0,"distN":125,"mixedPot":0.06282,"mixedPotCI":0.01594,"mixedBB":1.2328,"tv":0.5018,"tvCI":0.0394,"pBest":0.4855,"confidence":0.2293},"facingBet":{"n":75,"score":55.31,"scoreCI":10.26,"lossPot":0.08767,"lossPotCI":0.02962,"lossBB":2.7161,"lossBBCI":1.2259,"best":0.28,"approved":0.36,"blunder":0.1067,"invalid":0,"distN":75,"mixedPot":0.1094,"mixedPotCI":0.0249,"mixedBB":4.9238,"tv":0.6109,"tvCI":0.0532,"pBest":0.336,"confidence":0.1825}},"latency":{"mean":17.76,"median":17.18,"p90":23.499},"cost":{"total":0.013105,"per1k":0.0655},"tokens":{"prompt":262108,"completion":200,"promptPerDecision":1311},"inputPricePerM":0.05,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:22:10Z"},{"key":"solar-decide-flash","model":"upstage/solar-decide-flash","name":"Upstage Solar Decide Flash","kind":"decisionModel","provider":"Upstage","servedBy":"Upstage","resolvedModel":"upstage/solar-decide-flash-20261008","url":"https://openrouter.ai/upstage/solar-decide-flash","variant":"v2","label":"upstage/solar-decide-flash [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":64.09,"scoreCI":6.02,"lossPot":0.07729,"lossPotCI":0.02216,"lossBB":3.3719,"lossBBCI":2.1019,"best":0.42,"approved":0.47,"blunder":0.105,"invalid":0,"distN":200,"mixedPot":0.09062,"mixedPotCI":0.01495,"mixedBB":3.0339,"tv":0.5651,"tvCI":0.0222,"pBest":0.4032,"confidence":0.1162},"byStreet":{"turn":{"n":99,"score":62.82,"scoreCI":8.74,"lossPot":0.09314,"lossPotCI":0.03133,"lossBB":2.058,"lossBBCI":0.8477,"best":0.404,"approved":0.4444,"blunder":0.1414,"invalid":0,"distN":99,"mixedPot":0.11283,"mixedPotCI":0.02256,"mixedBB":2.1674,"tv":0.5785,"tvCI":0.0307,"pBest":0.407,"confidence":0.1203},"river":{"n":101,"score":65.33,"scoreCI":8.33,"lossPot":0.06176,"lossPotCI":0.03121,"lossBB":4.6598,"lossBBCI":4.0731,"best":0.4356,"approved":0.495,"blunder":0.0693,"invalid":0,"distN":101,"mixedPot":0.06884,"mixedPotCI":0.01885,"mixedBB":3.8833,"tv":0.5518,"tvCI":0.0321,"pBest":0.3996,"confidence":0.1122}},"byType":{"firstToAct":{"n":125,"score":68.64,"scoreCI":7.27,"lossPot":0.04885,"lossPotCI":0.01871,"lossBB":0.9203,"lossBBCI":0.5028,"best":0.496,"approved":0.512,"blunder":0.048,"invalid":0,"distN":125,"mixedPot":0.06709,"mixedPotCI":0.01553,"mixedBB":1.301,"tv":0.5354,"tvCI":0.0253,"pBest":0.446,"confidence":0.1246},"facingBet":{"n":75,"score":56.49,"scoreCI":10.38,"lossPot":0.1247,"lossPotCI":0.04856,"lossBB":7.4579,"lossBBCI":5.4396,"best":0.2933,"approved":0.4,"blunder":0.2,"invalid":0,"distN":75,"mixedPot":0.12982,"mixedPotCI":0.02832,"mixedBB":5.9222,"tv":0.6145,"tvCI":0.0395,"pBest":0.332,"confidence":0.1022}},"latency":{"mean":1.057,"median":0.99,"p90":1.491},"cost":{"total":0.013105,"per1k":0.0655},"tokens":{"prompt":262108,"completion":200,"promptPerDecision":1311},"inputPricePerM":0.05,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:53Z"},{"key":"kev-4b","model":"jaredpalmer/kev-4b","name":"Kev 4B","kind":"decisionModel","provider":"Jared Palmer","servedBy":"SiliconFlow","resolvedModel":"jaredpalmer/kev-4b-20260924","url":"https://openrouter.ai/jaredpalmer/kev-4b","variant":"v2","label":"jaredpalmer/kev-4b [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":58.37,"scoreCI":6.41,"lossPot":0.06263,"lossPotCI":0.01467,"lossBB":1.779,"lossBBCI":0.9192,"best":0.465,"approved":0.48,"blunder":0.06,"invalid":0,"distN":200,"mixedPot":0.08823,"mixedPotCI":0.01199,"mixedBB":2.7253,"tv":0.5694,"tvCI":0.0251,"pBest":0.3981,"confidence":0.1673},"byStreet":{"turn":{"n":99,"score":61.95,"scoreCI":9.03,"lossPot":0.06664,"lossPotCI":0.02218,"lossBB":1.0908,"lossBBCI":0.5176,"best":0.5051,"approved":0.4848,"blunder":0.0606,"invalid":0,"distN":99,"mixedPot":0.10223,"mixedPotCI":0.0172,"mixedBB":1.8184,"tv":0.571,"tvCI":0.0351,"pBest":0.4198,"confidence":0.1891},"river":{"n":101,"score":54.86,"scoreCI":9.09,"lossPot":0.05871,"lossPotCI":0.01935,"lossBB":2.4535,"lossBBCI":1.7426,"best":0.4257,"approved":0.4752,"blunder":0.0594,"invalid":0,"distN":101,"mixedPot":0.07451,"mixedPotCI":0.01636,"mixedBB":3.6143,"tv":0.5679,"tvCI":0.0362,"pBest":0.3768,"confidence":0.1459}},"byType":{"firstToAct":{"n":125,"score":45.84,"scoreCI":7.93,"lossPot":0.07702,"lossPotCI":0.01734,"lossBB":1.2549,"lossBBCI":0.4709,"best":0.288,"approved":0.288,"blunder":0.04,"invalid":0,"distN":125,"mixedPot":0.0753,"mixedPotCI":0.01134,"mixedBB":1.3812,"tv":0.6457,"tvCI":0.0276,"pBest":0.3417,"confidence":0.1161},"facingBet":{"n":75,"score":79.25,"scoreCI":9.1,"lossPot":0.03866,"lossPotCI":0.0256,"lossBB":2.6523,"lossBBCI":2.3186,"best":0.76,"approved":0.8,"blunder":0.0933,"invalid":0,"distN":75,"mixedPot":0.10978,"mixedPotCI":0.02516,"mixedBB":4.9654,"tv":0.4423,"tvCI":0.0326,"pBest":0.492,"confidence":0.2526}},"latency":{"mean":1.283,"median":1.116,"p90":2.084},"cost":{"total":0.009108,"per1k":0.0455},"tokens":{"prompt":216847,"completion":15007,"promptPerDecision":1084},"inputPricePerM":0.042,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:55Z"},{"key":"random","model":"baseline:random","name":"Random","kind":"baseline","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":57.16,"scoreCI":6.23,"lossPot":0.09563,"lossPotCI":0.02606,"lossBB":2.6697,"lossBBCI":1.5535,"best":0.395,"approved":0.41,"blunder":0.11,"invalid":0},"byStreet":{"turn":{"n":99,"score":50.82,"scoreCI":9.11,"lossPot":0.1223,"lossPotCI":0.04094,"lossBB":2.1839,"lossBBCI":0.7094,"best":0.3535,"approved":0.3434,"blunder":0.1515,"invalid":0},"river":{"n":101,"score":63.39,"scoreCI":8.39,"lossPot":0.06948,"lossPotCI":0.03182,"lossBB":3.146,"lossBBCI":3.0014,"best":0.4356,"approved":0.4752,"blunder":0.0693,"invalid":0}},"byType":{"firstToAct":{"n":125,"score":54.8,"scoreCI":7.97,"lossPot":0.07344,"lossPotCI":0.02129,"lossBB":1.3687,"lossBBCI":0.5907,"best":0.392,"approved":0.376,"blunder":0.072,"invalid":0},"facingBet":{"n":75,"score":61.1,"scoreCI":9.99,"lossPot":0.13261,"lossPotCI":0.05907,"lossBB":4.8381,"lossBBCI":3.9926,"best":0.4,"approved":0.4667,"blunder":0.1733,"invalid":0}},"updatedAt":"2026-10-09T19:08:30Z"},{"key":"tev1-4b-experimental","model":"togethercomputer/tev1-4b-experimental","name":"Together Tev1 4B (exp.)","kind":"decisionModel","provider":"Together AI","servedBy":"Together","resolvedModel":"togethercomputer/tev1-4b-experimental-20260923","url":"https://openrouter.ai/togethercomputer/tev1-4b-experimental","variant":"v2","label":"togethercomputer/tev1-4b-experimental [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":57.04,"scoreCI":5.98,"lossPot":0.07423,"lossPotCI":0.01712,"lossBB":2.0953,"lossBBCI":0.8193,"best":0.325,"approved":0.365,"blunder":0.07,"invalid":0,"distN":200,"mixedPot":0.07695,"mixedPotCI":0.01085,"mixedBB":2.2687,"tv":0.5839,"tvCI":0.025,"pBest":0.3931,"confidence":0.5087},"byStreet":{"turn":{"n":99,"score":50.26,"scoreCI":8.68,"lossPot":0.10145,"lossPotCI":0.02569,"lossBB":2.262,"lossBBCI":0.7348,"best":0.2525,"approved":0.2626,"blunder":0.1212,"invalid":0,"distN":99,"mixedPot":0.09723,"mixedPotCI":0.0166,"mixedBB":1.9406,"tv":0.6192,"tvCI":0.0343,"pBest":0.3779,"confidence":0.4988},"river":{"n":101,"score":63.69,"scoreCI":8.08,"lossPot":0.04755,"lossPotCI":0.0216,"lossBB":1.9319,"lossBBCI":1.4575,"best":0.396,"approved":0.4653,"blunder":0.0198,"invalid":0,"distN":101,"mixedPot":0.05707,"mixedPotCI":0.01299,"mixedBB":2.5902,"tv":0.5492,"tvCI":0.0352,"pBest":0.408,"confidence":0.5184}},"byType":{"firstToAct":{"n":125,"score":59.97,"scoreCI":7.25,"lossPot":0.06127,"lossPotCI":0.01674,"lossBB":1.1269,"lossBBCI":0.3974,"best":0.344,"approved":0.368,"blunder":0.04,"invalid":0,"distN":125,"mixedPot":0.0662,"mixedPotCI":0.01147,"mixedBB":1.1901,"tv":0.6047,"tvCI":0.0306,"pBest":0.3928,"confidence":0.5032},"facingBet":{"n":75,"score":52.16,"scoreCI":10.39,"lossPot":0.09583,"lossPotCI":0.03579,"lossBB":3.7094,"lossBBCI":2.0386,"best":0.2933,"approved":0.36,"blunder":0.12,"invalid":0,"distN":75,"mixedPot":0.09487,"mixedPotCI":0.02122,"mixedBB":4.0663,"tv":0.5491,"tvCI":0.0421,"pBest":0.3935,"confidence":0.5179}},"latency":{"mean":0.402,"median":0.38,"p90":0.46},"cost":{"total":0.008935,"per1k":0.0447},"tokens":{"prompt":212749,"completion":400,"promptPerDecision":1064},"inputPricePerM":0.042,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:54Z"},{"key":"clef-flash","model":"cloudflare/clef-flash","name":"Cloudflare Clef Flash","kind":"decisionModel","provider":"Cloudflare","servedBy":"PrimeIntellect","resolvedModel":"cloudflare/clef-flash","url":"https://openrouter.ai/cloudflare/clef-flash","variant":"v2","label":"cloudflare/clef-flash [v2]","answered":200,"total":200,"complete":true,"overall":{"n":200,"score":47.07,"scoreCI":6.51,"lossPot":0.07741,"lossPotCI":0.01362,"lossBB":1.6517,"lossBBCI":0.4707,"best":0.32,"approved":0.39,"blunder":0.065,"invalid":0,"distN":200,"mixedPot":0.0844,"mixedPotCI":0.00984,"mixedBB":2.3372,"tv":0.577,"tvCI":0.0239,"pBest":0.3874,"confidence":0.1453},"byStreet":{"turn":{"n":99,"score":44.03,"scoreCI":9.28,"lossPot":0.10318,"lossPotCI":0.02296,"lossBB":2.2182,"lossBBCI":0.7835,"best":0.303,"approved":0.3434,"blunder":0.1111,"invalid":0,"distN":99,"mixedPot":0.10725,"mixedPotCI":0.01576,"mixedBB":2.0882,"tv":0.604,"tvCI":0.0317,"pBest":0.387,"confidence":0.1459},"river":{"n":101,"score":50.05,"scoreCI":9.13,"lossPot":0.05215,"lossPotCI":0.01322,"lossBB":1.0965,"lossBBCI":0.5095,"best":0.3366,"approved":0.4356,"blunder":0.0198,"invalid":0,"distN":101,"mixedPot":0.062,"mixedPotCI":0.01019,"mixedBB":2.5814,"tv":0.5505,"tvCI":0.0352,"pBest":0.3878,"confidence":0.1447}},"byType":{"firstToAct":{"n":125,"score":34.4,"scoreCI":7.96,"lossPot":0.08973,"lossPotCI":0.0163,"lossBB":1.4801,"lossBBCI":0.4839,"best":0.264,"approved":0.28,"blunder":0.056,"invalid":0,"distN":125,"mixedPot":0.07523,"mixedPotCI":0.01086,"mixedBB":1.3572,"tv":0.6177,"tvCI":0.0281,"pBest":0.3684,"confidence":0.1453},"facingBet":{"n":75,"score":68.19,"scoreCI":9.46,"lossPot":0.05687,"lossPotCI":0.02351,"lossBB":1.9379,"lossBBCI":0.9635,"best":0.4133,"approved":0.5733,"blunder":0.08,"invalid":0,"distN":75,"mixedPot":0.09968,"mixedPotCI":0.01858,"mixedBB":3.9707,"tv":0.5092,"tvCI":0.0391,"pBest":0.419,"confidence":0.1453}},"latency":{"mean":0.675,"median":0.498,"p90":0.821},"cost":{"total":0.005522,"per1k":0.0276},"tokens":{"prompt":220603,"completion":0,"promptPerDecision":1103},"inputPricePerM":0.025,"inputPriceSource":"billed","stateVersion":1,"updatedAt":"2026-10-09T19:21:52Z"}],"file":"results.json"},"suites":[{"key":"cash-preflop","id":"20261009-170305-preflop300-cash-n650-s1","name":"Cash 100bb · preflop · 300 hands · 650 decisions · seed 1","mode":"preflop","format":{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"column":"cash-pre","root":"20261009-170305-preflop300-cash-n650-s1","split":null,"createdAt":"2026-10-09T20:03:05Z","decisions":650,"hands":300,"solves":1,"seed":"1","streets":{"preflop":650},"meanExplPctPot":0.028,"file":"suites/cash-preflop.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":650,"total":650,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":300,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"BB":0,"SB":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":650,"total":650,"complete":true,"score":99.98,"scoreCI":0.01,"lossPot":0.00021,"lossPotCI":0.00011,"mixedPot":0.00021,"best":0.98,"blunder":0,"invalid":0,"tv":0,"pBest":0.9774,"perHand":{"hands":300,"bb":0.04,"ci":0.02,"mixed":0.04,"mixedCI":0.01,"bySeat":{"BB":0,"SB":0.07}}},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":300,"total":650,"complete":false,"score":93.84,"scoreCI":1.57,"lossPot":0.04349,"lossPotCI":0.01178,"mixedPot":0.05429,"best":0.69,"blunder":0.09,"invalid":0,"tv":0.3487,"pBest":0.6551,"perHand":{"hands":140,"bb":9.08,"ci":2.37,"mixed":15.97,"mixedCI":4.93,"bySeat":{"BB":4.47,"SB":13.7}},"cost":0.02886},{"key":"gpt-6-luna-decisions-nuts","label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","answered":300,"total":650,"complete":false,"score":92.54,"scoreCI":1.96,"lossPot":0.04779,"lossPotCI":0.01269,"mixedPot":0.05103,"best":0.6867,"blunder":0.0967,"invalid":0,"tv":0.3214,"pBest":0.6773,"perHand":{"hands":140,"bb":20.69,"ci":14.07,"mixed":23.44,"mixedCI":16.58,"bySeat":{"BB":20.4,"SB":20.98}},"cost":0.03658},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":650,"total":650,"complete":true,"score":90.38,"scoreCI":1.4,"lossPot":0.06666,"lossPotCI":0.01187,"mixedPot":null,"best":0.5892,"blunder":0.0785,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":300,"bb":22.42,"ci":10.58,"mixed":null,"mixedCI":null,"bySeat":{"BB":22.09,"SB":22.74}}},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":650,"total":650,"complete":true,"score":55.12,"scoreCI":3.23,"lossPot":0.28441,"lossPotCI":0.02487,"mixedPot":null,"best":0.2569,"blunder":0.44,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":300,"bb":78.4,"ci":11.64,"mixed":null,"mixedCI":null,"bySeat":{"BB":71.14,"SB":85.66}}}]},{"key":"cash-preflop-2","id":"20261009-175307-preflop120-cash-n268-s35","name":"Preflop cash","mode":"preflop","format":{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"column":"cash-pre","root":"20261009-175307-preflop120-cash-n268-s35","split":null,"createdAt":"2026-10-09T20:53:07Z","decisions":268,"hands":120,"solves":1,"seed":"35","streets":{"preflop":268},"meanExplPctPot":0.028,"file":null,"players":[]},{"key":"cash-hands","id":"20261009-170429-hands120-cash-n661-s31","name":"Cash 100bb · full hands","mode":"hands","format":{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"column":"cash-post","root":"20261009-170429-hands120-cash-n661-s31","split":null,"createdAt":"2026-10-09T20:04:29Z","decisions":661,"hands":120,"solves":40,"seed":"31","streets":{"flop":305,"turn":213,"river":143},"meanExplPctPot":0.669,"file":null,"players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":661,"total":661,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":120,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"IP":0,"OOP":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":661,"total":661,"complete":true,"score":95.93,"scoreCI":1.43,"lossPot":0.00111,"lossPotCI":0.00087,"mixedPot":0.00105,"best":0.9259,"blunder":0.0015,"invalid":0,"tv":0,"pBest":0.9301,"perHand":{"hands":120,"bb":8.47,"ci":8.9,"mixed":8.34,"mixedCI":8.88,"bySeat":{"IP":2.16,"OOP":14.79}}},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":661,"total":661,"complete":true,"score":79.77,"scoreCI":2.93,"lossPot":0.04525,"lossPotCI":0.00881,"mixedPot":null,"best":0.7428,"blunder":0.0862,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":120,"bb":337.67,"ci":95.3,"mixed":null,"mixedCI":null,"bySeat":{"IP":400.05,"OOP":275.3}}},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":661,"total":661,"complete":true,"score":61.19,"scoreCI":3.59,"lossPot":0.09436,"lossPotCI":0.01303,"mixedPot":null,"best":0.534,"blunder":0.1604,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":120,"bb":545.71,"ci":120.91,"mixed":null,"mixedCI":null,"bySeat":{"IP":532.62,"OOP":558.81}}}]},{"key":"cash-hands-dev","id":"20261009-170429-hands120-cash-n661-s31-dev","name":"Cash 100bb · full hands · dev","mode":"hands","format":{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"column":"cash-post","root":"20261009-170429-hands120-cash-n661-s31","split":"dev","createdAt":"2026-10-09T20:04:29Z","decisions":337,"hands":60,"solves":40,"seed":"31","streets":{"flop":155,"turn":109,"river":73},"meanExplPctPot":0.663,"file":"suites/cash-hands-dev.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","borrowed":true,"answered":337,"total":337,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"IP":0,"OOP":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","borrowed":true,"answered":337,"total":337,"complete":true,"score":96.75,"scoreCI":1.81,"lossPot":0.00069,"lossPotCI":0.00029,"mixedPot":0.00067,"best":0.9377,"blunder":0,"invalid":0,"tv":0,"pBest":0.9372,"perHand":{"hands":60,"bb":4.55,"ci":3.33,"mixed":4.8,"mixedCI":3.05,"bySeat":{"IP":0.67,"OOP":8.44}}},{"key":"ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--multi-","label":"Luna self-ensemble (eqrange+multi)","name":"Luna self-ensemble (eqrange+multi)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--multi-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi"]},"answered":337,"total":337,"complete":true,"score":85.21,"scoreCI":3.7,"lossPot":0.02236,"lossPotCI":0.01145,"mixedPot":0.03508,"best":0.8131,"blunder":0.0178,"invalid":0,"tv":0.3013,"pBest":0.7568,"perHand":{"hands":60,"bb":128.7,"ci":108.43,"mixed":187.38,"mixedCI":101.41,"bySeat":{"IP":194.76,"OOP":62.64}},"cost":0.0928},{"key":"gpt-6-luna-decisions-multi","label":"openai/gpt-6-luna-decisions [multi]","name":"GPT-6 Luna Decisions [multi]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"multi","answered":337,"total":337,"complete":true,"score":85.05,"scoreCI":3.66,"lossPot":0.02714,"lossPotCI":0.01175,"mixedPot":0.04185,"best":0.8012,"blunder":0.0356,"invalid":0,"tv":0.3169,"pBest":0.7404,"perHand":{"hands":60,"bb":147.69,"ci":100.31,"mixed":218.4,"mixedCI":96.17,"bySeat":{"IP":184.34,"OOP":111.05}},"cost":0.05573},{"key":"gpt-6-luna-decisions-eqrange","label":"openai/gpt-6-luna-decisions [eqrange]","name":"GPT-6 Luna Decisions [eqrange]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eqrange","answered":337,"total":337,"complete":true,"score":85,"scoreCI":3.74,"lossPot":0.02155,"lossPotCI":0.01125,"mixedPot":0.02831,"best":0.8131,"blunder":0.0148,"invalid":0,"tv":0.2978,"pBest":0.7731,"perHand":{"hands":60,"bb":146.55,"ci":139.79,"mixed":156.36,"mixedCI":112.78,"bySeat":{"IP":227.65,"OOP":65.44}},"cost":0.03707},{"key":"temper2-gpt-6-luna-decisions--eqrange-","label":"gpt-6-luna-decisions [eqrange] τ=2","name":"gpt-6-luna-decisions [eqrange] τ=2","kind":"derived","model":"derived:temper2-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = 2 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"answered":337,"total":337,"complete":true,"score":85,"scoreCI":3.74,"lossPot":0.02155,"lossPotCI":0.01125,"mixedPot":0.02398,"best":0.8131,"blunder":0.0148,"invalid":0,"tv":0.2923,"pBest":0.7949,"perHand":{"hands":60,"bb":146.55,"ci":139.79,"mixed":146.31,"mixedCI":122.32,"bySeat":{"IP":227.65,"OOP":65.44}},"cost":0.03707},{"key":"temper4-gpt-6-luna-decisions--eqrange-","label":"gpt-6-luna-decisions [eqrange] τ=4","name":"gpt-6-luna-decisions [eqrange] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"answered":337,"total":337,"complete":true,"score":85,"scoreCI":3.74,"lossPot":0.02155,"lossPotCI":0.01125,"mixedPot":0.02235,"best":0.8131,"blunder":0.0148,"invalid":0,"tv":0.2949,"pBest":0.8044,"perHand":{"hands":60,"bb":146.55,"ci":139.79,"mixed":141.11,"mixedCI":123.37,"bySeat":{"IP":227.65,"OOP":65.44}},"cost":0.03707},{"key":"temperinf-gpt-6-luna-decisions--eqrange-","label":"gpt-6-luna-decisions [eqrange] τ=inf","name":"gpt-6-luna-decisions [eqrange] τ=inf","kind":"derived","model":"derived:temperinf-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = inf and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"answered":337,"total":337,"complete":true,"score":85,"scoreCI":3.74,"lossPot":0.02155,"lossPotCI":0.01125,"mixedPot":0.02094,"best":0.8131,"blunder":0.0148,"invalid":0,"tv":0.2991,"pBest":0.816,"perHand":{"hands":60,"bb":146.55,"ci":139.79,"mixed":144.99,"mixedCI":139.82,"bySeat":{"IP":227.65,"OOP":65.44}},"cost":0.03707},{"key":"guard-narrowed0-gpt-6-luna-decisions--eqrange-","label":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +0%) [hybrid]","name":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +0%) [hybrid]","kind":"derived","model":"derived:guard-narrowed0-gpt-6-luna-decisions--eqrange-","derived":{"method":"guardrail","description":"HYBRID (not a pure model): fold probability moved to call when heuristic equity vs the villain's narrowed range ≥ price + 0%.","hybrid":true,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"answered":337,"total":337,"complete":true,"score":85,"scoreCI":3.74,"lossPot":0.02155,"lossPotCI":0.01125,"mixedPot":0.0279,"best":0.8131,"blunder":0.0148,"invalid":0,"tv":0.2982,"pBest":0.7737,"perHand":{"hands":60,"bb":146.55,"ci":139.79,"mixed":154.39,"mixedCI":111.7,"bySeat":{"IP":227.65,"OOP":65.44}},"cost":0.03707},{"key":"guard-narrowed5-gpt-6-luna-decisions--eqrange-","label":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +5%) [hybrid]","name":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +5%) [hybrid]","kind":"derived","model":"derived:guard-narrowed5-gpt-6-luna-decisions--eqrange-","derived":{"method":"guardrail","description":"HYBRID (not a pure model): fold probability moved to call when heuristic equity vs the villain's narrowed range ≥ price + 5%.","hybrid":true,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"answered":337,"total":337,"complete":true,"score":85,"scoreCI":3.74,"lossPot":0.02155,"lossPotCI":0.01125,"mixedPot":0.0279,"best":0.8131,"blunder":0.0148,"invalid":0,"tv":0.2976,"pBest":0.7736,"perHand":{"hands":60,"bb":146.55,"ci":139.79,"mixed":154.43,"mixedCI":111.71,"bySeat":{"IP":227.65,"OOP":65.44}},"cost":0.03707},{"key":"ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--nuts-","label":"Luna ensemble (eqrange+nuts)","name":"Luna ensemble (eqrange+nuts)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--nuts-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__nuts"]},"answered":337,"total":337,"complete":true,"score":84.69,"scoreCI":3.77,"lossPot":0.02267,"lossPotCI":0.01145,"mixedPot":0.0285,"best":0.8101,"blunder":0.0178,"invalid":0,"tv":0.297,"pBest":0.7753,"perHand":{"hands":60,"bb":124.52,"ci":108.06,"mixed":152.41,"mixedCI":110.9,"bySeat":{"IP":174.01,"OOP":75.03}},"cost":0.07831},{"key":"gpt-6-luna-decisions-coach","label":"openai/gpt-6-luna-decisions [coach]","name":"GPT-6 Luna Decisions [coach]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"coach","answered":337,"total":337,"complete":true,"score":84.67,"scoreCI":3.68,"lossPot":0.03294,"lossPotCI":0.0133,"mixedPot":0.0484,"best":0.7893,"blunder":0.0415,"invalid":0,"tv":0.3324,"pBest":0.72,"perHand":{"hands":60,"bb":213.02,"ci":135.34,"mixed":251.28,"mixedCI":106.92,"bySeat":{"IP":288.29,"OOP":137.76}},"cost":0.03086},{"key":"ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--eq--gpt-6-luna-decisions--multi--gpt-6-luna-decisions--v2--gpt-6-luna-decisions--noul-","label":"Luna self-ensemble (5 variants)","name":"Luna self-ensemble (5 variants)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--eq--gpt-6-luna-decisions--multi--gpt-6-luna-decisions--v2--gpt-6-luna-decisions--noul-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eq","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__noul"]},"answered":337,"total":337,"complete":true,"score":84.65,"scoreCI":3.72,"lossPot":0.02596,"lossPotCI":0.01158,"mixedPot":0.03833,"best":0.8012,"blunder":0.0297,"invalid":0,"tv":0.3138,"pBest":0.7491,"perHand":{"hands":60,"bb":138.01,"ci":99.63,"mixed":198.61,"mixedCI":91.23,"bySeat":{"IP":167.95,"OOP":108.07}},"cost":0.20407},{"key":"ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--v2--gpt-6-luna-decisions--multi-","label":"Luna self-ensemble (eqrange+v2+multi)","name":"Luna self-ensemble (eqrange+v2+multi)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--v2--gpt-6-luna-decisions--multi-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi"]},"answered":337,"total":337,"complete":true,"score":84.39,"scoreCI":3.72,"lossPot":0.02868,"lossPotCI":0.0125,"mixedPot":0.03618,"best":0.7953,"blunder":0.0326,"invalid":0,"tv":0.3065,"pBest":0.7544,"perHand":{"hands":60,"bb":161.88,"ci":110.82,"mixed":193.32,"mixedCI":100.06,"bySeat":{"IP":228.79,"OOP":94.97}},"cost":0.12399},{"key":"gpt-6-luna-decisions-nuts","label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","answered":337,"total":337,"complete":true,"score":84.39,"scoreCI":3.8,"lossPot":0.02239,"lossPotCI":0.01143,"mixedPot":0.02868,"best":0.8042,"blunder":0.0178,"invalid":0,"tv":0.2991,"pBest":0.7775,"perHand":{"hands":60,"bb":120.16,"ci":107.76,"mixed":148.46,"mixedCI":109.75,"bySeat":{"IP":165.44,"OOP":74.88}},"cost":0.04124},{"key":"temper4-gpt-6-luna-decisions--nuts-","label":"gpt-6-luna-decisions [nuts] τ=4","name":"gpt-6-luna-decisions [nuts] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--nuts-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__nuts"]},"answered":337,"total":337,"complete":true,"score":84.39,"scoreCI":3.8,"lossPot":0.02239,"lossPotCI":0.01143,"mixedPot":0.02347,"best":0.8042,"blunder":0.0178,"invalid":0,"tv":0.3023,"pBest":0.8017,"perHand":{"hands":60,"bb":120.16,"ci":107.76,"mixed":125.9,"mixedCI":108.11,"bySeat":{"IP":165.44,"OOP":74.88}},"cost":0.04124},{"key":"gpt-6-luna-decisions-eq","label":"openai/gpt-6-luna-decisions [eq]","name":"GPT-6 Luna Decisions [eq]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eq","answered":337,"total":337,"complete":true,"score":84.22,"scoreCI":3.71,"lossPot":0.0311,"lossPotCI":0.01261,"mixedPot":0.03655,"best":0.7893,"blunder":0.0356,"invalid":0,"tv":0.3257,"pBest":0.76,"perHand":{"hands":60,"bb":167.14,"ci":108.92,"mixed":186.82,"mixedCI":98.35,"bySeat":{"IP":247.83,"OOP":86.44}},"cost":0.035},{"key":"d1","label":"liquid/d1 [v2]","name":"Liquid d1","kind":"decisionModel","model":"liquid/d1","modelName":"Liquid d1","variant":"v2","answered":200,"total":337,"complete":false,"score":84.19,"scoreCI":4.82,"lossPot":0.03143,"lossPotCI":0.01827,"mixedPot":0.04009,"best":0.765,"blunder":0.02,"invalid":0,"tv":0.3711,"pBest":0.7216,"perHand":{"hands":35,"bb":198.81,"ci":182.23,"mixed":251.67,"mixedCI":152.44,"bySeat":{"IP":293.52,"OOP":104.1}},"cost":0.00883},{"key":"gpt-6-luna-decisions-sizing","label":"openai/gpt-6-luna-decisions [sizing]","name":"GPT-6 Luna Decisions [sizing]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"sizing","answered":337,"total":337,"complete":true,"score":84.08,"scoreCI":3.83,"lossPot":0.02275,"lossPotCI":0.01153,"mixedPot":0.02662,"best":0.7982,"blunder":0.0208,"invalid":0,"tv":0.2999,"pBest":0.7768,"perHand":{"hands":60,"bb":120.75,"ci":107.71,"mixed":138.42,"mixedCI":87.32,"bySeat":{"IP":165.22,"OOP":76.28}},"cost":0.04298},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":337,"total":337,"complete":true,"score":83.44,"scoreCI":3.82,"lossPot":0.02888,"lossPotCI":0.01189,"mixedPot":0.03839,"best":0.7864,"blunder":0.0356,"invalid":0,"tv":0.3219,"pBest":0.7495,"perHand":{"hands":60,"bb":155.95,"ci":100.59,"mixed":205.2,"mixedCI":98.87,"bySeat":{"IP":196.02,"OOP":115.88}},"cost":0.03119},{"key":"temper2-gpt-6-luna-decisions--v2-","label":"gpt-6-luna-decisions [v2] τ=2","name":"gpt-6-luna-decisions [v2] τ=2","kind":"derived","model":"derived:temper2-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = 2 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"answered":337,"total":337,"complete":true,"score":83.44,"scoreCI":3.82,"lossPot":0.02888,"lossPotCI":0.01189,"mixedPot":0.0306,"best":0.7864,"blunder":0.0356,"invalid":0,"tv":0.3149,"pBest":0.7775,"perHand":{"hands":60,"bb":155.95,"ci":100.59,"mixed":162.46,"mixedCI":80.73,"bySeat":{"IP":196.02,"OOP":115.88}},"cost":0.03119},{"key":"temper4-gpt-6-luna-decisions--v2-","label":"gpt-6-luna-decisions [v2] τ=4","name":"gpt-6-luna-decisions [v2] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"answered":337,"total":337,"complete":true,"score":83.44,"scoreCI":3.82,"lossPot":0.02888,"lossPotCI":0.01189,"mixedPot":0.02758,"best":0.7864,"blunder":0.0356,"invalid":0,"tv":0.32,"pBest":0.7883,"perHand":{"hands":60,"bb":155.95,"ci":100.59,"mixed":144.33,"mixedCI":75.59,"bySeat":{"IP":196.02,"OOP":115.88}},"cost":0.03119},{"key":"temperinf-gpt-6-luna-decisions--v2-","label":"gpt-6-luna-decisions [v2] τ=inf","name":"gpt-6-luna-decisions [v2] τ=inf","kind":"derived","model":"derived:temperinf-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = inf and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"answered":337,"total":337,"complete":true,"score":83.44,"scoreCI":3.82,"lossPot":0.02888,"lossPotCI":0.01189,"mixedPot":0.02888,"best":0.7864,"blunder":0.0356,"invalid":0,"tv":0.3325,"pBest":0.7864,"perHand":{"hands":60,"bb":155.95,"ci":100.59,"mixed":155.95,"mixedCI":100.59,"bySeat":{"IP":196.02,"OOP":115.88}},"cost":0.03119},{"key":"gpt-6-luna-decisions-noul","label":"openai/gpt-6-luna-decisions [noul]","name":"GPT-6 Luna Decisions [noul]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"noul","answered":337,"total":337,"complete":true,"score":83,"scoreCI":3.85,"lossPot":0.03327,"lossPotCI":0.01021,"mixedPot":0.04823,"best":0.7834,"blunder":0.0534,"invalid":0.0059,"tv":0.3517,"pBest":0.7179,"perHand":{"hands":60,"bb":150.68,"ci":54.76,"mixed":242.04,"mixedCI":75.89,"bySeat":{"IP":142.27,"OOP":159.09}},"cost":0.04508},{"key":"mercury-decide-free-nuts","label":"inception/mercury-decide:free [nuts]","name":"Inception Mercury Decide (free endpoint) [nuts]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"nuts","answered":337,"total":337,"complete":true,"score":82.17,"scoreCI":4.01,"lossPot":0.01793,"lossPotCI":0.00627,"mixedPot":0.02708,"best":0.7804,"blunder":0.0148,"invalid":0,"tv":0.3215,"pBest":0.7491,"perHand":{"hands":60,"bb":61.76,"ci":29.67,"mixed":105.19,"mixedCI":39.75,"bySeat":{"IP":45.09,"OOP":78.43}},"cost":0},{"key":"jev-1.13","label":"typesafe/jev-1.13 [v2]","name":"TypeSafe Jev 1.13","kind":"decisionModel","model":"typesafe/jev-1.13","modelName":"TypeSafe Jev 1.13","variant":"v2","answered":205,"total":337,"complete":false,"score":81.96,"scoreCI":5.08,"lossPot":0.024,"lossPotCI":0.00979,"mixedPot":0.05168,"best":0.7463,"blunder":0.0195,"invalid":0,"tv":0.3845,"pBest":0.6609,"perHand":{"hands":35,"bb":145.59,"ci":95.67,"mixed":284.17,"mixedCI":111.66,"bySeat":{"IP":167.27,"OOP":123.9}},"cost":0.01181},{"key":"mercury-decide-free-sizing","label":"inception/mercury-decide:free [sizing]","name":"Inception Mercury Decide (free endpoint) [sizing]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"sizing","answered":337,"total":337,"complete":true,"score":81.85,"scoreCI":4.02,"lossPot":0.02134,"lossPotCI":0.00797,"mixedPot":0.02724,"best":0.7745,"blunder":0.0178,"invalid":0,"tv":0.3329,"pBest":0.7458,"perHand":{"hands":60,"bb":93.6,"ci":62.06,"mixed":112.29,"mixedCI":47.72,"bySeat":{"IP":111.14,"OOP":76.06}},"cost":0},{"key":"gpt-6-luna-decisions-minimal","label":"openai/gpt-6-luna-decisions [minimal]","name":"GPT-6 Luna Decisions [minimal]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"minimal","answered":337,"total":337,"complete":true,"score":80.42,"scoreCI":4.08,"lossPot":0.04131,"lossPotCI":0.01249,"mixedPot":0.04714,"best":0.7567,"blunder":0.0623,"invalid":0,"tv":0.3457,"pBest":0.7249,"perHand":{"hands":60,"bb":231.3,"ci":106.6,"mixed":257.33,"mixedCI":113.54,"bySeat":{"IP":232.49,"OOP":230.12}},"cost":0.0141},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","borrowed":true,"answered":337,"total":337,"complete":true,"score":79.47,"scoreCI":4.13,"lossPot":0.04809,"lossPotCI":0.01292,"mixedPot":null,"best":0.7418,"blunder":0.0772,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":265.08,"ci":91.38,"mixed":null,"mixedCI":null,"bySeat":{"IP":277.04,"OOP":253.13}}},{"key":"mercury-decide-free","label":"inception/mercury-decide:free [v2]","name":"Inception Mercury Decide (free endpoint)","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"v2","answered":337,"total":337,"complete":true,"score":74.9,"scoreCI":4.41,"lossPot":0.0435,"lossPotCI":0.01311,"mixedPot":0.05254,"best":0.6736,"blunder":0.0475,"invalid":0,"tv":0.4116,"pBest":0.6501,"perHand":{"hands":60,"bb":219,"ci":113.09,"mixed":241.35,"mixedCI":89.76,"bySeat":{"IP":285.31,"OOP":152.7}},"cost":0},{"key":"mercury-decide","label":"inception/mercury-decide [v2]","name":"Inception Mercury Decide","kind":"decisionModel","model":"inception/mercury-decide","modelName":"Inception Mercury Decide","variant":"v2","answered":200,"total":337,"complete":false,"score":74.64,"scoreCI":5.72,"lossPot":0.04612,"lossPotCI":0.01485,"mixedPot":0.05515,"best":0.655,"blunder":0.05,"invalid":0,"tv":0.4231,"pBest":0.6419,"perHand":{"hands":35,"bb":243.12,"ci":123.46,"mixed":296.44,"mixedCI":137.83,"bySeat":{"IP":284.06,"OOP":202.18}},"cost":0.00398},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","borrowed":true,"answered":337,"total":337,"complete":true,"score":62.7,"scoreCI":5.05,"lossPot":0.09346,"lossPotCI":0.01941,"mixedPot":null,"best":0.5816,"blunder":0.1543,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":428.81,"ci":148.51,"mixed":null,"mixedCI":null,"bySeat":{"IP":397.39,"OOP":460.23}}}]},{"key":"cash-hands-test","id":"20261009-170429-hands120-cash-n661-s31-test","name":"Cash 100bb · full hands · test","mode":"hands","format":{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"column":"cash-post","root":"20261009-170429-hands120-cash-n661-s31","split":"test","createdAt":"2026-10-09T20:04:29Z","decisions":324,"hands":60,"solves":40,"seed":"31","streets":{"flop":150,"turn":104,"river":70},"meanExplPctPot":0.674,"file":"suites/cash-hands-test.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","borrowed":true,"answered":324,"total":324,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"IP":0,"OOP":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","borrowed":true,"answered":324,"total":324,"complete":true,"score":95.08,"scoreCI":2.24,"lossPot":0.00155,"lossPotCI":0.00175,"mixedPot":0.00144,"best":0.9136,"blunder":0.0031,"invalid":0,"tv":0,"pBest":0.9226,"perHand":{"hands":60,"bb":12.4,"ci":17.5,"mixed":11.87,"mixedCI":17.53,"bySeat":{"IP":3.65,"OOP":21.14}}},{"key":"gpt-6-luna-decisions-multi","label":"openai/gpt-6-luna-decisions [multi]","name":"GPT-6 Luna Decisions [multi]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"multi","answered":324,"total":324,"complete":true,"score":85.81,"scoreCI":3.64,"lossPot":0.02219,"lossPotCI":0.00826,"mixedPot":0.03416,"best":0.8025,"blunder":0.0401,"invalid":0,"tv":0.3037,"pBest":0.7421,"perHand":{"hands":60,"bb":183.8,"ci":95.04,"mixed":275.92,"mixedCI":99.9,"bySeat":{"IP":214.62,"OOP":152.98}},"cost":0.05468},{"key":"temper4-gpt-6-luna-decisions--multi-","label":"gpt-6-luna-decisions [multi] τ=4","name":"gpt-6-luna-decisions [multi] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--multi-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-test__openai_gpt-6-luna-decisions__multi"]},"answered":324,"total":324,"complete":true,"score":85.81,"scoreCI":3.64,"lossPot":0.02219,"lossPotCI":0.00826,"mixedPot":0.02375,"best":0.8025,"blunder":0.0401,"invalid":0,"tv":0.2942,"pBest":0.7946,"perHand":{"hands":60,"bb":183.8,"ci":95.04,"mixed":199.96,"mixedCI":96.21,"bySeat":{"IP":214.62,"OOP":152.98}},"cost":0.05468},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":324,"total":324,"complete":true,"score":85.74,"scoreCI":3.62,"lossPot":0.02193,"lossPotCI":0.00848,"mixedPot":0.03356,"best":0.7994,"blunder":0.037,"invalid":0,"tv":0.3055,"pBest":0.7432,"perHand":{"hands":60,"bb":178.92,"ci":90.95,"mixed":276.87,"mixedCI":105.01,"bySeat":{"IP":210.16,"OOP":147.68}},"cost":0.03059},{"key":"temper4-gpt-6-luna-decisions--v2-","label":"gpt-6-luna-decisions [v2] τ=4","name":"gpt-6-luna-decisions [v2] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-test__openai_gpt-6-luna-decisions"]},"answered":324,"total":324,"complete":true,"score":85.74,"scoreCI":3.62,"lossPot":0.02193,"lossPotCI":0.00848,"mixedPot":0.02364,"best":0.7994,"blunder":0.037,"invalid":0,"tv":0.2992,"pBest":0.7908,"perHand":{"hands":60,"bb":178.92,"ci":90.95,"mixed":190.82,"mixedCI":90.36,"bySeat":{"IP":210.16,"OOP":147.68}},"cost":0.03059},{"key":"gpt-6-luna-decisions-eqrange","label":"openai/gpt-6-luna-decisions [eqrange]","name":"GPT-6 Luna Decisions [eqrange]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eqrange","answered":324,"total":324,"complete":true,"score":85.33,"scoreCI":3.74,"lossPot":0.01589,"lossPotCI":0.00668,"mixedPot":0.02059,"best":0.787,"blunder":0.0216,"invalid":0,"tv":0.2755,"pBest":0.7682,"perHand":{"hands":60,"bb":146.25,"ci":93.8,"mixed":160.74,"mixedCI":87.15,"bySeat":{"IP":166.63,"OOP":125.87}},"cost":0.03634},{"key":"temper4-gpt-6-luna-decisions--eqrange-","label":"gpt-6-luna-decisions [eqrange] τ=4","name":"gpt-6-luna-decisions [eqrange] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-test__openai_gpt-6-luna-decisions__eqrange"]},"answered":324,"total":324,"complete":true,"score":85.33,"scoreCI":3.74,"lossPot":0.01589,"lossPotCI":0.00668,"mixedPot":0.01643,"best":0.787,"blunder":0.0216,"invalid":0,"tv":0.2896,"pBest":0.7846,"perHand":{"hands":60,"bb":146.25,"ci":93.8,"mixed":147.39,"mixedCI":93.01,"bySeat":{"IP":166.63,"OOP":125.87}},"cost":0.03634},{"key":"clef-nuts","label":"cloudflare/clef [nuts]","name":"Cloudflare Clef [nuts]","kind":"decisionModel","model":"cloudflare/clef","modelName":"Cloudflare Clef","variant":"nuts","answered":324,"total":324,"complete":true,"score":85.27,"scoreCI":3.74,"lossPot":0.01691,"lossPotCI":0.00719,"mixedPot":0.04724,"best":0.784,"blunder":0.0278,"invalid":0,"tv":0.3699,"pBest":0.6684,"perHand":{"hands":60,"bb":133.95,"ci":89.07,"mixed":304.65,"mixedCI":85.67,"bySeat":{"IP":132.95,"OOP":134.95}},"cost":0.10117},{"key":"gpt-6-luna-decisions-nuts","label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","answered":324,"total":324,"complete":true,"score":84.28,"scoreCI":3.85,"lossPot":0.01523,"lossPotCI":0.00619,"mixedPot":0.02111,"best":0.784,"blunder":0.0185,"invalid":0,"tv":0.274,"pBest":0.7635,"perHand":{"hands":60,"bb":141.71,"ci":93.36,"mixed":158.33,"mixedCI":86.63,"bySeat":{"IP":158.83,"OOP":124.59}},"cost":0.04036},{"key":"temper4-gpt-6-luna-decisions--nuts-","label":"gpt-6-luna-decisions [nuts] τ=4","name":"gpt-6-luna-decisions [nuts] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--nuts-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-test__openai_gpt-6-luna-decisions__nuts"]},"answered":324,"total":324,"complete":true,"score":84.28,"scoreCI":3.85,"lossPot":0.01523,"lossPotCI":0.00619,"mixedPot":0.01642,"best":0.784,"blunder":0.0185,"invalid":0,"tv":0.2862,"pBest":0.7806,"perHand":{"hands":60,"bb":141.71,"ci":93.36,"mixed":145.25,"mixedCI":92.21,"bySeat":{"IP":158.83,"OOP":124.59}},"cost":0.04036},{"key":"ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--nuts-","label":"Luna ensemble (eqrange+nuts)","name":"Luna ensemble (eqrange+nuts)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--nuts-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-test__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-test__openai_gpt-6-luna-decisions__nuts"]},"answered":324,"total":324,"complete":true,"score":84.02,"scoreCI":3.87,"lossPot":0.01584,"lossPotCI":0.00627,"mixedPot":0.02085,"best":0.7778,"blunder":0.0185,"invalid":0,"tv":0.273,"pBest":0.7658,"perHand":{"hands":60,"bb":147.6,"ci":93.46,"mixed":159.53,"mixedCI":86.83,"bySeat":{"IP":170.21,"OOP":124.99}},"cost":0.0767},{"key":"gpt-6-luna-decisions-sizing","label":"openai/gpt-6-luna-decisions [sizing]","name":"GPT-6 Luna Decisions [sizing]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"sizing","answered":324,"total":324,"complete":true,"score":83.97,"scoreCI":3.89,"lossPot":0.01744,"lossPotCI":0.00698,"mixedPot":0.02236,"best":0.7778,"blunder":0.0247,"invalid":0,"tv":0.2825,"pBest":0.7579,"perHand":{"hands":60,"bb":143.13,"ci":93.53,"mixed":172.15,"mixedCI":92.99,"bySeat":{"IP":154.16,"OOP":132.09}},"cost":0.04222},{"key":"mercury-decide-free-nuts","label":"inception/mercury-decide:free [nuts]","name":"Inception Mercury Decide (free endpoint) [nuts]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"nuts","answered":324,"total":324,"complete":true,"score":82.96,"scoreCI":3.95,"lossPot":0.02276,"lossPotCI":0.00824,"mixedPot":0.02721,"best":0.7562,"blunder":0.0309,"invalid":0,"tv":0.3306,"pBest":0.7326,"perHand":{"hands":60,"bb":153.5,"ci":94.9,"mixed":168.78,"mixedCI":85.97,"bySeat":{"IP":155.5,"OOP":151.49}},"cost":0},{"key":"clef","label":"cloudflare/clef [v2]","name":"Cloudflare Clef","kind":"decisionModel","model":"cloudflare/clef","modelName":"Cloudflare Clef","variant":"v2","answered":324,"total":324,"complete":true,"score":82.21,"scoreCI":3.94,"lossPot":0.03102,"lossPotCI":0.00993,"mixedPot":0.06485,"best":0.7377,"blunder":0.0586,"invalid":0,"tv":0.4179,"pBest":0.6127,"perHand":{"hands":60,"bb":274.01,"ci":132.13,"mixed":470.21,"mixedCI":128.39,"bySeat":{"IP":280.53,"OOP":267.5}},"cost":0.07719},{"key":"mercury-decide-free-sizing","label":"inception/mercury-decide:free [sizing]","name":"Inception Mercury Decide (free endpoint) [sizing]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"sizing","answered":324,"total":324,"complete":true,"score":81.99,"scoreCI":4,"lossPot":0.02649,"lossPotCI":0.00879,"mixedPot":0.02944,"best":0.7315,"blunder":0.037,"invalid":0,"tv":0.3534,"pBest":0.7203,"perHand":{"hands":60,"bb":167.08,"ci":95.03,"mixed":178.61,"mixedCI":87.05,"bySeat":{"IP":168.19,"OOP":165.96}},"cost":0},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","borrowed":true,"answered":324,"total":324,"complete":true,"score":80.08,"scoreCI":4.16,"lossPot":0.0423,"lossPotCI":0.01195,"mixedPot":null,"best":0.7438,"blunder":0.0957,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":410.27,"ci":166.13,"mixed":null,"mixedCI":null,"bySeat":{"IP":523.07,"OOP":297.47}}},{"key":"mercury-decide-free","label":"inception/mercury-decide:free [v2]","name":"Inception Mercury Decide (free endpoint)","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"v2","answered":324,"total":324,"complete":true,"score":75.58,"scoreCI":4.4,"lossPot":0.04281,"lossPotCI":0.01051,"mixedPot":0.04968,"best":0.6451,"blunder":0.0586,"invalid":0,"tv":0.4157,"pBest":0.6322,"perHand":{"hands":60,"bb":270.35,"ci":128.22,"mixed":328.87,"mixedCI":113.11,"bySeat":{"IP":315.51,"OOP":225.2}},"cost":0},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","borrowed":true,"answered":324,"total":324,"complete":true,"score":59.63,"scoreCI":5.11,"lossPot":0.09529,"lossPotCI":0.01734,"mixedPot":null,"best":0.4846,"blunder":0.1667,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":662.61,"ci":187.45,"mixed":null,"mixedCI":null,"bySeat":{"IP":667.84,"OOP":657.38}}}]},{"key":"mtt40-preflop","id":"20261009-175309-preflop120-mtt40-n276-s35","name":"Preflop mtt40","mode":"preflop","format":{"id":"mtt40","title":"Tournament · 40bb (ante)","short":"MTT 40bb","summary":"Mid-stage tournament: 40bb effective, 2.2x opens, 1bb big-blind ante. Chip EV (no ICM)."},"column":"mtt40-pre","root":"20261009-175309-preflop120-mtt40-n276-s35","split":null,"createdAt":"2026-10-09T20:53:09Z","decisions":276,"hands":120,"solves":1,"seed":"35","streets":{"preflop":276},"meanExplPctPot":0.018,"file":null,"players":[]},{"key":"mtt40-hands","id":"20261009-171911-hands60-mtt40-n295-s32","name":"MTT 40bb · full hands","mode":"hands","format":{"id":"mtt40","title":"Tournament · 40bb (ante)","short":"MTT 40bb","summary":"Mid-stage tournament: 40bb effective, 2.2x opens, 1bb big-blind ante. Chip EV (no ICM)."},"column":"mtt40-post","root":"20261009-171911-hands60-mtt40-n295-s32","split":null,"createdAt":"2026-10-09T20:19:11Z","decisions":295,"hands":60,"solves":20,"seed":"32","streets":{"flop":143,"turn":91,"river":61},"meanExplPctPot":0.695,"file":"suites/mtt40-hands.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":295,"total":295,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"IP":0,"OOP":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":295,"total":295,"complete":true,"score":97.99,"scoreCI":1.43,"lossPot":0.00077,"lossPotCI":0.00032,"mixedPot":0.00103,"best":0.9186,"blunder":0,"invalid":0,"tv":0,"pBest":0.8973,"perHand":{"hands":60,"bb":2.43,"ci":1.28,"mixed":3.48,"mixedCI":1.07,"bySeat":{"IP":2.84,"OOP":2.01}}},{"key":"gpt-6-luna-decisions-nuts","label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","answered":295,"total":295,"complete":true,"score":92.56,"scoreCI":2.71,"lossPot":0.01393,"lossPotCI":0.00692,"mixedPot":0.01949,"best":0.8034,"blunder":0.0169,"invalid":0,"tv":0.2803,"pBest":0.7721,"perHand":{"hands":60,"bb":55.08,"ci":32.01,"mixed":67.88,"mixedCI":31.5,"bySeat":{"IP":55.23,"OOP":54.93}},"cost":0.03947},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":295,"total":295,"complete":true,"score":87.95,"scoreCI":3.42,"lossPot":0.022,"lossPotCI":0.00884,"mixedPot":0.03016,"best":0.7695,"blunder":0.0305,"invalid":0,"tv":0.3051,"pBest":0.728,"perHand":{"hands":60,"bb":88.59,"ci":47.03,"mixed":141.55,"mixedCI":58.21,"bySeat":{"IP":64.13,"OOP":113.05}},"cost":0.03067},{"key":"mercury-decide-free-nuts","label":"inception/mercury-decide:free [nuts]","name":"Inception Mercury Decide (free endpoint) [nuts]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"nuts","answered":295,"total":295,"complete":true,"score":87.31,"scoreCI":3.38,"lossPot":0.02306,"lossPotCI":0.00893,"mixedPot":0.02895,"best":0.7051,"blunder":0.0373,"invalid":0,"tv":0.3571,"pBest":0.687,"perHand":{"hands":60,"bb":73.7,"ci":34.79,"mixed":85.7,"mixedCI":32.45,"bySeat":{"IP":72.15,"OOP":75.25}},"cost":0},{"key":"mercury-decide-free-sizing","label":"inception/mercury-decide:free [sizing]","name":"Inception Mercury Decide (free endpoint) [sizing]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"sizing","answered":295,"total":295,"complete":true,"score":86.45,"scoreCI":3.45,"lossPot":0.02487,"lossPotCI":0.00905,"mixedPot":0.02945,"best":0.678,"blunder":0.0373,"invalid":0,"tv":0.3827,"pBest":0.667,"perHand":{"hands":60,"bb":78.7,"ci":35.7,"mixed":87.82,"mixedCI":32.98,"bySeat":{"IP":75.06,"OOP":82.33}},"cost":0},{"key":"mercury-decide-free","label":"inception/mercury-decide:free [v2]","name":"Inception Mercury Decide (free endpoint)","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"v2","answered":295,"total":295,"complete":true,"score":85.81,"scoreCI":3.52,"lossPot":0.02447,"lossPotCI":0.00824,"mixedPot":0.03611,"best":0.678,"blunder":0.0305,"invalid":0,"tv":0.384,"pBest":0.6177,"perHand":{"hands":60,"bb":100.21,"ci":43.66,"mixed":135.96,"mixedCI":34.86,"bySeat":{"IP":135.91,"OOP":64.5}},"cost":0},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":295,"total":295,"complete":true,"score":79.94,"scoreCI":4.23,"lossPot":0.04173,"lossPotCI":0.01183,"mixedPot":null,"best":0.7017,"blunder":0.0678,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":188.04,"ci":53.33,"mixed":null,"mixedCI":null,"bySeat":{"IP":251.67,"OOP":124.41}}},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":295,"total":295,"complete":true,"score":52.77,"scoreCI":5.34,"lossPot":0.13371,"lossPotCI":0.02124,"mixedPot":null,"best":0.3661,"blunder":0.2169,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":457.32,"ci":137.42,"mixed":null,"mixedCI":null,"bySeat":{"IP":533.81,"OOP":380.84}}}]},{"key":"mtt20-preflop","id":"20261009-170155-preflop50-mtt20-n117-s3","name":"MTT 20bb · preflop · 50 hands · 117 decisions · seed 3","mode":"preflop","format":{"id":"mtt20","title":"Tournament · 20bb (ante)","short":"MTT 20bb","summary":"Late-stage tournament: 20bb effective, 2x opens, 1bb big-blind ante, low SPR. Chip EV (no ICM)."},"column":"mtt20-pre","root":"20261009-170155-preflop50-mtt20-n117-s3","split":null,"createdAt":"2026-10-09T20:01:55Z","decisions":117,"hands":50,"solves":1,"seed":"3","streets":{"preflop":117},"meanExplPctPot":0.013,"file":"suites/mtt20-preflop.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":117,"total":117,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":50,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"BB":0,"SB":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":117,"total":117,"complete":true,"score":99.99,"scoreCI":0.01,"lossPot":0.00003,"lossPotCI":0.00004,"mixedPot":0.00007,"best":1,"blunder":0,"invalid":0,"tv":0,"pBest":0.9938,"perHand":{"hands":50,"bb":0.02,"ci":0.03,"mixed":0.03,"mixedCI":0.03,"bySeat":{"BB":0.05,"SB":0}}},{"key":"gpt-6-luna-decisions-shortstack","label":"openai/gpt-6-luna-decisions [shortstack]","name":"GPT-6 Luna Decisions [shortstack]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"shortstack","answered":117,"total":117,"complete":true,"score":84.01,"scoreCI":6.09,"lossPot":0.04598,"lossPotCI":0.02261,"mixedPot":0.04246,"best":0.735,"blunder":0.0513,"invalid":0,"tv":0.2922,"pBest":0.7299,"perHand":{"hands":50,"bb":27.11,"ci":15.82,"mixed":27.44,"mixedCI":14.87,"bySeat":{"BB":34.82,"SB":19.4}},"cost":0.01197},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":117,"total":117,"complete":true,"score":71.36,"scoreCI":6.9,"lossPot":0.08781,"lossPotCI":0.02631,"mixedPot":0.10646,"best":0.547,"blunder":0.1111,"invalid":0,"tv":0.5153,"pBest":0.4964,"perHand":{"hands":50,"bb":36.88,"ci":15.14,"mixed":48.3,"mixedCI":14.59,"bySeat":{"BB":30.52,"SB":43.24}},"cost":0.01074},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":117,"total":117,"complete":true,"score":70.18,"scoreCI":7.95,"lossPot":0.05967,"lossPotCI":0.01868,"mixedPot":null,"best":0.5983,"blunder":0.0598,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":50,"bb":81.81,"ci":29.94,"mixed":null,"mixedCI":null,"bySeat":{"BB":54.41,"SB":109.21}}},{"key":"gpt-6-luna-decisions-nuts","label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","answered":117,"total":117,"complete":true,"score":64.55,"scoreCI":7.46,"lossPot":0.12057,"lossPotCI":0.03068,"mixedPot":0.11928,"best":0.4786,"blunder":0.2051,"invalid":0,"tv":0.5267,"pBest":0.4886,"perHand":{"hands":50,"bb":36.71,"ci":8.24,"mixed":36.74,"mixedCI":7.2,"bySeat":{"BB":13.46,"SB":59.96}},"cost":0.01363},{"key":"gpt-6-luna-decisions-eq","label":"openai/gpt-6-luna-decisions [eq]","name":"GPT-6 Luna Decisions [eq]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eq","answered":117,"total":117,"complete":true,"score":58.93,"scoreCI":7.77,"lossPot":0.11673,"lossPotCI":0.02905,"mixedPot":0.1246,"best":0.4274,"blunder":0.188,"invalid":0,"tv":0.5868,"pBest":0.4244,"perHand":{"hands":50,"bb":43.4,"ci":11.72,"mixed":46.11,"mixedCI":8.82,"bySeat":{"BB":19.06,"SB":67.74}},"cost":0.0119},{"key":"gpt-6-luna-decisions-coach","label":"openai/gpt-6-luna-decisions [coach]","name":"GPT-6 Luna Decisions [coach]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"coach","answered":117,"total":117,"complete":true,"score":57.51,"scoreCI":7.83,"lossPot":0.14262,"lossPotCI":0.03243,"mixedPot":0.1314,"best":0.4017,"blunder":0.2393,"invalid":0,"tv":0.6026,"pBest":0.4046,"perHand":{"hands":50,"bb":44.27,"ci":8.24,"mixed":55.6,"mixedCI":9.34,"bySeat":{"BB":16.29,"SB":72.26}},"cost":0.01132},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":117,"total":117,"complete":true,"score":50.8,"scoreCI":7.9,"lossPot":0.14197,"lossPotCI":0.03021,"mixedPot":null,"best":0.2991,"blunder":0.2137,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":50,"bb":77.87,"ci":22.65,"mixed":null,"mixedCI":null,"bySeat":{"BB":48.98,"SB":106.77}}}]},{"key":"mtt20-preflop-2","id":"20261009-175311-preflop120-mtt20-n290-s35","name":"Preflop mtt20","mode":"preflop","format":{"id":"mtt20","title":"Tournament · 20bb (ante)","short":"MTT 20bb","summary":"Late-stage tournament: 20bb effective, 2x opens, 1bb big-blind ante, low SPR. Chip EV (no ICM)."},"column":"mtt20-pre","root":"20261009-175311-preflop120-mtt20-n290-s35","split":null,"createdAt":"2026-10-09T20:53:11Z","decisions":290,"hands":120,"solves":1,"seed":"35","streets":{"preflop":290},"meanExplPctPot":0.013,"file":null,"players":[]},{"key":"mtt20-hands","id":"20261009-173433-hands60-mtt20-n300-s33","name":"MTT 20bb · full hands","mode":"hands","format":{"id":"mtt20","title":"Tournament · 20bb (ante)","short":"MTT 20bb","summary":"Late-stage tournament: 20bb effective, 2x opens, 1bb big-blind ante, low SPR. Chip EV (no ICM)."},"column":"mtt20-post","root":"20261009-173433-hands60-mtt20-n300-s33","split":null,"createdAt":"2026-10-09T20:34:33Z","decisions":300,"hands":60,"solves":20,"seed":"33","streets":{"flop":139,"turn":104,"river":57},"meanExplPctPot":0.611,"file":"suites/mtt20-hands.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":300,"total":300,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"IP":0,"OOP":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":300,"total":300,"complete":true,"score":96.71,"scoreCI":1.73,"lossPot":0.00152,"lossPotCI":0.00081,"mixedPot":0.00143,"best":0.9,"blunder":0,"invalid":0,"tv":0,"pBest":0.9016,"perHand":{"hands":60,"bb":4.08,"ci":2.64,"mixed":3.7,"mixedCI":1.93,"bySeat":{"IP":3.26,"OOP":4.9}}},{"key":"mercury-decide-nuts","label":"inception/mercury-decide [nuts]","name":"Inception Mercury Decide [nuts]","kind":"decisionModel","model":"inception/mercury-decide","modelName":"Inception Mercury Decide","variant":"nuts","answered":300,"total":300,"complete":true,"score":88.87,"scoreCI":3.07,"lossPot":0.02089,"lossPotCI":0.00878,"mixedPot":0.02942,"best":0.74,"blunder":0.02,"invalid":0,"tv":0.3412,"pBest":0.6875,"perHand":{"hands":60,"bb":43.85,"ci":19.99,"mixed":57.43,"mixedCI":16.53,"bySeat":{"IP":56.8,"OOP":30.9}},"cost":0.00843},{"key":"gpt-6-luna-decisions-nuts","label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","answered":300,"total":300,"complete":true,"score":88.69,"scoreCI":3.21,"lossPot":0.01862,"lossPotCI":0.00855,"mixedPot":0.02314,"best":0.7633,"blunder":0.02,"invalid":0,"tv":0.2975,"pBest":0.7401,"perHand":{"hands":60,"bb":39.73,"ci":18.55,"mixed":47.47,"mixedCI":17.49,"bySeat":{"IP":43.17,"OOP":36.29}},"cost":0.0396},{"key":"mercury-decide-free-nuts","label":"inception/mercury-decide:free [nuts]","name":"Inception Mercury Decide (free endpoint) [nuts]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"nuts","answered":300,"total":300,"complete":true,"score":88.58,"scoreCI":3.12,"lossPot":0.02148,"lossPotCI":0.00884,"mixedPot":0.02943,"best":0.7367,"blunder":0.02,"invalid":0,"tv":0.3411,"pBest":0.6882,"perHand":{"hands":60,"bb":44.66,"ci":20.11,"mixed":57.44,"mixedCI":16.57,"bySeat":{"IP":56.8,"OOP":32.52}},"cost":0},{"key":"d1-nuts","label":"liquid/d1 [nuts]","name":"Liquid d1 [nuts]","kind":"decisionModel","model":"liquid/d1","modelName":"Liquid d1","variant":"nuts","answered":300,"total":300,"complete":true,"score":88.41,"scoreCI":3.2,"lossPot":0.0179,"lossPotCI":0.00821,"mixedPot":0.02367,"best":0.7467,"blunder":0.01,"invalid":0,"tv":0.3153,"pBest":0.7157,"perHand":{"hands":60,"bb":35.9,"ci":16.4,"mixed":48.03,"mixedCI":14.21,"bySeat":{"IP":37.21,"OOP":34.59}},"cost":0.0185},{"key":"clef-nuts","label":"cloudflare/clef [nuts]","name":"Cloudflare Clef [nuts]","kind":"decisionModel","model":"cloudflare/clef","modelName":"Cloudflare Clef","variant":"nuts","answered":300,"total":300,"complete":true,"score":88.2,"scoreCI":3.29,"lossPot":0.01842,"lossPotCI":0.00663,"mixedPot":0.05561,"best":0.76,"blunder":0.01,"invalid":0,"tv":0.4333,"pBest":0.5603,"perHand":{"hands":60,"bb":33.69,"ci":12.33,"mixed":108.1,"mixedCI":18.13,"bySeat":{"IP":37.79,"OOP":29.58}},"cost":0.09924},{"key":"mercury-decide-free-sizing","label":"inception/mercury-decide:free [sizing]","name":"Inception Mercury Decide (free endpoint) [sizing]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"sizing","answered":300,"total":300,"complete":true,"score":86.6,"scoreCI":3.34,"lossPot":0.02636,"lossPotCI":0.00958,"mixedPot":0.03431,"best":0.7167,"blunder":0.02,"invalid":0,"tv":0.3681,"pBest":0.6648,"perHand":{"hands":60,"bb":48.76,"ci":19.33,"mixed":62.58,"mixedCI":16.53,"bySeat":{"IP":62.76,"OOP":34.75}},"cost":0},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":300,"total":300,"complete":true,"score":86.48,"scoreCI":3.52,"lossPot":0.02488,"lossPotCI":0.00967,"mixedPot":0.03495,"best":0.74,"blunder":0.0367,"invalid":0,"tv":0.336,"pBest":0.7004,"perHand":{"hands":60,"bb":56.43,"ci":21.01,"mixed":88.2,"mixedCI":29.79,"bySeat":{"IP":69.86,"OOP":43}},"cost":0.03056},{"key":"jev-1.13-nuts","label":"typesafe/jev-1.13 [nuts]","name":"TypeSafe Jev 1.13 [nuts]","kind":"decisionModel","model":"typesafe/jev-1.13","modelName":"TypeSafe Jev 1.13","variant":"nuts","answered":300,"total":300,"complete":true,"score":85.58,"scoreCI":3.42,"lossPot":0.0242,"lossPotCI":0.00728,"mixedPot":0.0331,"best":0.6833,"blunder":0.0167,"invalid":0,"tv":0.3605,"pBest":0.6496,"perHand":{"hands":60,"bb":46.25,"ci":17.34,"mixed":61.78,"mixedCI":13.83,"bySeat":{"IP":50.96,"OOP":41.54}},"cost":0.02281},{"key":"d1","label":"liquid/d1 [v2]","name":"Liquid d1","kind":"decisionModel","model":"liquid/d1","modelName":"Liquid d1","variant":"v2","answered":300,"total":300,"complete":true,"score":85.31,"scoreCI":3.56,"lossPot":0.02396,"lossPotCI":0.00932,"mixedPot":0.03198,"best":0.7267,"blunder":0.0167,"invalid":0,"tv":0.351,"pBest":0.6857,"perHand":{"hands":60,"bb":58.98,"ci":34.59,"mixed":76.35,"mixedCI":24.47,"bySeat":{"IP":76.76,"OOP":41.21}},"cost":0.01438},{"key":"jev-1.13","label":"typesafe/jev-1.13 [v2]","name":"TypeSafe Jev 1.13","kind":"decisionModel","model":"typesafe/jev-1.13","modelName":"TypeSafe Jev 1.13","variant":"v2","answered":300,"total":300,"complete":true,"score":85.09,"scoreCI":3.48,"lossPot":0.0271,"lossPotCI":0.00966,"mixedPot":0.04912,"best":0.6833,"blunder":0.02,"invalid":0,"tv":0.3915,"pBest":0.5947,"perHand":{"hands":60,"bb":63.44,"ci":35.72,"mixed":114.87,"mixedCI":31.11,"bySeat":{"IP":90.09,"OOP":36.8}},"cost":0.01856},{"key":"clef","label":"cloudflare/clef [v2]","name":"Cloudflare Clef","kind":"decisionModel","model":"cloudflare/clef","modelName":"Cloudflare Clef","variant":"v2","answered":300,"total":300,"complete":true,"score":82.66,"scoreCI":3.83,"lossPot":0.03353,"lossPotCI":0.00963,"mixedPot":0.07134,"best":0.68,"blunder":0.0333,"invalid":0,"tv":0.4838,"pBest":0.5059,"perHand":{"hands":60,"bb":80.22,"ci":36.42,"mixed":161.83,"mixedCI":33.16,"bySeat":{"IP":96.46,"OOP":63.97}},"cost":0.07703},{"key":"mercury-decide","label":"inception/mercury-decide [v2]","name":"Inception Mercury Decide","kind":"decisionModel","model":"inception/mercury-decide","modelName":"Inception Mercury Decide","variant":"v2","answered":300,"total":300,"complete":true,"score":80.78,"scoreCI":3.87,"lossPot":0.03708,"lossPotCI":0.01034,"mixedPot":0.04792,"best":0.6333,"blunder":0.0333,"invalid":0,"tv":0.4201,"pBest":0.5949,"perHand":{"hands":60,"bb":82.68,"ci":31.86,"mixed":109.55,"mixedCI":31.07,"bySeat":{"IP":80.15,"OOP":85.21}},"cost":0.00654},{"key":"mercury-decide-free","label":"inception/mercury-decide:free [v2]","name":"Inception Mercury Decide (free endpoint)","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"v2","answered":300,"total":300,"complete":true,"score":80.41,"scoreCI":3.87,"lossPot":0.03833,"lossPotCI":0.01038,"mixedPot":0.04832,"best":0.62,"blunder":0.0333,"invalid":0,"tv":0.4193,"pBest":0.5952,"perHand":{"hands":60,"bb":84.58,"ci":31.65,"mixed":109.53,"mixedCI":30.81,"bySeat":{"IP":81.58,"OOP":87.58}},"cost":0},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":300,"total":300,"complete":true,"score":80.25,"scoreCI":4.2,"lossPot":0.04152,"lossPotCI":0.0113,"mixedPot":null,"best":0.6833,"blunder":0.0733,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":106.84,"ci":34.81,"mixed":null,"mixedCI":null,"bySeat":{"IP":92.58,"OOP":121.1}}},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":300,"total":300,"complete":true,"score":56.51,"scoreCI":5.21,"lossPot":0.10939,"lossPotCI":0.02374,"mixedPot":null,"best":0.4233,"blunder":0.14,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":256.54,"ci":97.48,"mixed":null,"mixedCI":null,"bySeat":{"IP":307.1,"OOP":205.99}}}]},{"key":"spin-preflop","id":"20261009-170307-preflop100-spin-n228-s1","name":"Spin & Go · preflop · 100 hands · 228 decisions · seed 1","mode":"preflop","format":{"id":"spin","title":"Spin & Go · 15–25bb","short":"Spin & Go","summary":"Hyper-turbo 3-max Spin & Go: 25bb 3-handed and 15bb heads-up, min-raises, very wide ranges. Chip EV."},"column":"spin-pre","root":"20261009-170307-preflop100-spin-n228-s1","split":null,"createdAt":"2026-10-09T20:03:07Z","decisions":228,"hands":100,"solves":2,"seed":"1","streets":{"preflop":228},"meanExplPctPot":0.062,"file":"suites/spin-preflop.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":228,"total":228,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":100,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"BB":0,"SB":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":228,"total":228,"complete":true,"score":99.84,"scoreCI":0.11,"lossPot":0.00066,"lossPotCI":0.00053,"mixedPot":0.00073,"best":0.9386,"blunder":0,"invalid":0,"tv":0,"pBest":0.943,"perHand":{"hands":100,"bb":0.17,"ci":0.16,"mixed":0.18,"mixedCI":0.14,"bySeat":{"BB":0.09,"SB":0.26}}},{"key":"gpt-6-luna-decisions-shortstack","label":"openai/gpt-6-luna-decisions [shortstack]","name":"GPT-6 Luna Decisions [shortstack]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"shortstack","answered":228,"total":228,"complete":true,"score":87.2,"scoreCI":3.78,"lossPot":0.03428,"lossPotCI":0.0137,"mixedPot":0.03917,"best":0.7281,"blunder":0.0351,"invalid":0,"tv":0.2962,"pBest":0.7055,"perHand":{"hands":100,"bb":8.92,"ci":4.42,"mixed":12.16,"mixedCI":4.08,"bySeat":{"BB":10.9,"SB":6.94}},"cost":0.02351},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":228,"total":228,"complete":true,"score":75.72,"scoreCI":4.95,"lossPot":0.09257,"lossPotCI":0.02377,"mixedPot":0.1088,"best":0.5658,"blunder":0.1535,"invalid":0,"tv":0.4896,"pBest":0.5148,"perHand":{"hands":100,"bb":18.63,"ci":5.08,"mixed":26.13,"mixedCI":3.71,"bySeat":{"BB":9.04,"SB":28.22}},"cost":0.02112},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":228,"total":228,"complete":true,"score":74.96,"scoreCI":5.22,"lossPot":0.04994,"lossPotCI":0.01534,"mixedPot":null,"best":0.5833,"blunder":0.0439,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":100,"bb":42.37,"ci":14.33,"mixed":null,"mixedCI":null,"bySeat":{"BB":32.9,"SB":51.84}}},{"key":"gpt-6-luna-decisions-nuts","label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","answered":228,"total":228,"complete":true,"score":73.41,"scoreCI":5.17,"lossPot":0.09861,"lossPotCI":0.0243,"mixedPot":0.11146,"best":0.5526,"blunder":0.1754,"invalid":0,"tv":0.4739,"pBest":0.5267,"perHand":{"hands":100,"bb":19.9,"ci":4.21,"mixed":22.59,"mixedCI":3.35,"bySeat":{"BB":5.9,"SB":33.91}},"cost":0.02676},{"key":"gpt-6-luna-decisions-coach","label":"openai/gpt-6-luna-decisions [coach]","name":"GPT-6 Luna Decisions [coach]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"coach","answered":228,"total":228,"complete":true,"score":70.12,"scoreCI":5.39,"lossPot":0.13599,"lossPotCI":0.03109,"mixedPot":0.12088,"best":0.5132,"blunder":0.2149,"invalid":0,"tv":0.5145,"pBest":0.4652,"perHand":{"hands":100,"bb":25.76,"ci":4.66,"mixed":30.38,"mixedCI":3.52,"bySeat":{"BB":4.83,"SB":46.69}},"cost":0.02216},{"key":"gpt-6-luna-decisions-eq","label":"openai/gpt-6-luna-decisions [eq]","name":"GPT-6 Luna Decisions [eq]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eq","answered":228,"total":228,"complete":true,"score":65.47,"scoreCI":5.64,"lossPot":0.10993,"lossPotCI":0.02371,"mixedPot":0.1229,"best":0.4693,"blunder":0.2018,"invalid":0,"tv":0.5577,"pBest":0.4514,"perHand":{"hands":100,"bb":27.2,"ci":5.68,"mixed":30.91,"mixedCI":4.43,"bySeat":{"BB":16.93,"SB":37.46}},"cost":0.02339},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":228,"total":228,"complete":true,"score":55.43,"scoreCI":5.59,"lossPot":0.16456,"lossPotCI":0.03486,"mixedPot":null,"best":0.2763,"blunder":0.2237,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":100,"bb":48.36,"ci":10.63,"mixed":null,"mixedCI":null,"bySeat":{"BB":35.94,"SB":60.78}}}]},{"key":"spin-preflop-2","id":"20261009-175312-preflop120-spin-n268-s35","name":"Preflop spin","mode":"preflop","format":{"id":"spin","title":"Spin & Go · 15–25bb","short":"Spin & Go","summary":"Hyper-turbo 3-max Spin & Go: 25bb 3-handed and 15bb heads-up, min-raises, very wide ranges. Chip EV."},"column":"spin-pre","root":"20261009-175312-preflop120-spin-n268-s35","split":null,"createdAt":"2026-10-09T20:53:12Z","decisions":268,"hands":120,"solves":2,"seed":"35","streets":{"preflop":268},"meanExplPctPot":0.062,"file":"suites/spin-preflop-2.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":268,"total":268,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":120,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"BB":0,"SB":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":268,"total":268,"complete":true,"score":99.57,"scoreCI":0.56,"lossPot":0.00036,"lossPotCI":0.00017,"mixedPot":0.00048,"best":0.9403,"blunder":0,"invalid":0,"tv":0,"pBest":0.9472,"perHand":{"hands":120,"bb":0.08,"ci":0.04,"mixed":0.1,"mixedCI":0.05,"bySeat":{"BB":0.08,"SB":0.09}}},{"key":"gpt-6-luna-decisions-shortstack","label":"openai/gpt-6-luna-decisions [shortstack]","name":"GPT-6 Luna Decisions [shortstack]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"shortstack","answered":268,"total":268,"complete":true,"score":84.63,"scoreCI":3.86,"lossPot":0.04921,"lossPotCI":0.01518,"mixedPot":0.05365,"best":0.6978,"blunder":0.0784,"invalid":0,"tv":0.313,"pBest":0.6889,"perHand":{"hands":120,"bb":17.85,"ci":9.36,"mixed":17.82,"mixedCI":5.77,"bySeat":{"BB":7.94,"SB":27.76}},"cost":0.02761},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":268,"total":268,"complete":true,"score":75.48,"scoreCI":4.8,"lossPot":0.06146,"lossPotCI":0.01641,"mixedPot":null,"best":0.6119,"blunder":0.0784,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":120,"bb":38.76,"ci":13.19,"mixed":null,"mixedCI":null,"bySeat":{"BB":23.59,"SB":53.93}}},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":268,"total":268,"complete":true,"score":70.96,"scoreCI":4.96,"lossPot":0.11069,"lossPotCI":0.02357,"mixedPot":0.1279,"best":0.5373,"blunder":0.1791,"invalid":0,"tv":0.5146,"pBest":0.4929,"perHand":{"hands":120,"bb":24.46,"ci":7.66,"mixed":33.45,"mixedCI":5.65,"bySeat":{"BB":8.22,"SB":40.7}},"cost":0.02479},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":268,"total":268,"complete":true,"score":54.55,"scoreCI":5.29,"lossPot":0.18139,"lossPotCI":0.04272,"mixedPot":null,"best":0.3396,"blunder":0.2388,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":120,"bb":53.61,"ci":12.89,"mixed":null,"mixedCI":null,"bySeat":{"BB":20.25,"SB":86.97}}}]},{"key":"spin-hands","id":"20261009-174215-hands60-spin-n312-s34","name":"Spin & Go · full hands","mode":"hands","format":{"id":"spin","title":"Spin & Go · 15–25bb","short":"Spin & Go","summary":"Hyper-turbo 3-max Spin & Go: 25bb 3-handed and 15bb heads-up, min-raises, very wide ranges. Chip EV."},"column":"spin-post","root":"20261009-174215-hands60-spin-n312-s34","split":null,"createdAt":"2026-10-09T20:42:15Z","decisions":312,"hands":60,"solves":20,"seed":"34","streets":{"flop":151,"turn":97,"river":64},"meanExplPctPot":0.624,"file":"suites/spin-hands.json","players":[{"key":"bestev","label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","answered":312,"total":312,"complete":true,"score":100,"scoreCI":0,"lossPot":0,"lossPotCI":0,"mixedPot":null,"best":1,"blunder":0,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"bySeat":{"IP":0,"OOP":0}}},{"key":"gto","label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","answered":312,"total":312,"complete":true,"score":98,"scoreCI":1.31,"lossPot":0.00076,"lossPotCI":0.00035,"mixedPot":0.00089,"best":0.9295,"blunder":0,"invalid":0,"tv":0,"pBest":0.9133,"perHand":{"hands":60,"bb":1.22,"ci":0.79,"mixed":1.41,"mixedCI":0.53,"bySeat":{"IP":1.13,"OOP":1.31}}},{"key":"gpt-6-luna-decisions-nuts","label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","answered":312,"total":312,"complete":true,"score":88.92,"scoreCI":3.26,"lossPot":0.01779,"lossPotCI":0.00741,"mixedPot":0.02699,"best":0.8109,"blunder":0.0192,"invalid":0,"tv":0.2916,"pBest":0.7329,"perHand":{"hands":60,"bb":28.32,"ci":13.06,"mixed":40.57,"mixedCI":13.14,"bySeat":{"IP":19.77,"OOP":36.87}},"cost":0.04096},{"key":"gpt-6-luna-decisions","label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","answered":312,"total":312,"complete":true,"score":86.98,"scoreCI":3.43,"lossPot":0.02713,"lossPotCI":0.00985,"mixedPot":0.03819,"best":0.7756,"blunder":0.0417,"invalid":0,"tv":0.2993,"pBest":0.7012,"perHand":{"hands":60,"bb":45.46,"ci":18.39,"mixed":61.95,"mixedCI":14.46,"bySeat":{"IP":28.9,"OOP":62.02}},"cost":0.03175},{"key":"mercury-decide-free-nuts","label":"inception/mercury-decide:free [nuts]","name":"Inception Mercury Decide (free endpoint) [nuts]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"nuts","answered":312,"total":312,"complete":true,"score":84.83,"scoreCI":3.64,"lossPot":0.02398,"lossPotCI":0.00789,"mixedPot":0.03419,"best":0.7179,"blunder":0.0224,"invalid":0,"tv":0.3689,"pBest":0.6655,"perHand":{"hands":60,"bb":36.15,"ci":15.17,"mixed":49.56,"mixedCI":12.55,"bySeat":{"IP":29.01,"OOP":43.3}},"cost":0},{"key":"mercury-decide-free-sizing","label":"inception/mercury-decide:free [sizing]","name":"Inception Mercury Decide (free endpoint) [sizing]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"sizing","answered":312,"total":312,"complete":true,"score":84.14,"scoreCI":3.63,"lossPot":0.0253,"lossPotCI":0.00722,"mixedPot":0.03495,"best":0.6955,"blunder":0.0192,"invalid":0,"tv":0.3904,"pBest":0.6522,"perHand":{"hands":60,"bb":37.29,"ci":13.65,"mixed":50.5,"mixedCI":12.31,"bySeat":{"IP":33.72,"OOP":40.87}},"cost":0},{"key":"mercury-decide-free","label":"inception/mercury-decide:free [v2]","name":"Inception Mercury Decide (free endpoint)","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"v2","answered":312,"total":312,"complete":true,"score":83.13,"scoreCI":3.72,"lossPot":0.03097,"lossPotCI":0.00853,"mixedPot":0.04581,"best":0.6795,"blunder":0.0288,"invalid":0,"tv":0.4064,"pBest":0.6059,"perHand":{"hands":60,"bb":50.32,"ci":15.42,"mixed":72.12,"mixedCI":12.76,"bySeat":{"IP":39.12,"OOP":61.51}},"cost":0},{"key":"callingstation","label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","answered":312,"total":312,"complete":true,"score":82.18,"scoreCI":4.01,"lossPot":0.04504,"lossPotCI":0.01261,"mixedPot":null,"best":0.7372,"blunder":0.0833,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":85.01,"ci":19.42,"mixed":null,"mixedCI":null,"bySeat":{"IP":80.93,"OOP":89.1}}},{"key":"random","label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","answered":312,"total":312,"complete":true,"score":59.17,"scoreCI":4.93,"lossPot":0.11013,"lossPotCI":0.01946,"mixedPot":null,"best":0.3846,"blunder":0.1699,"invalid":0,"tv":null,"pBest":null,"perHand":{"hands":60,"bb":152.77,"ci":26.58,"mixed":null,"mixedCI":null,"bySeat":{"IP":107.35,"OOP":198.2}}}]}],"formats":{"columns":[{"key":"cash-pre","format":{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"phase":"preflop","title":"Cash 100bb pre","suites":["cash-preflop","cash-preflop-2"],"hands":420},{"key":"cash-post","format":{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"phase":"postflop","title":"Cash 100bb post","suites":["cash-hands","cash-hands-dev","cash-hands-test"],"hands":120},{"key":"mtt40-pre","format":{"id":"mtt40","title":"Tournament · 40bb (ante)","short":"MTT 40bb","summary":"Mid-stage tournament: 40bb effective, 2.2x opens, 1bb big-blind ante. Chip EV (no ICM)."},"phase":"preflop","title":"MTT 40bb pre","suites":["mtt40-preflop"],"hands":120},{"key":"mtt40-post","format":{"id":"mtt40","title":"Tournament · 40bb (ante)","short":"MTT 40bb","summary":"Mid-stage tournament: 40bb effective, 2.2x opens, 1bb big-blind ante. Chip EV (no ICM)."},"phase":"postflop","title":"MTT 40bb post","suites":["mtt40-hands"],"hands":60},{"key":"mtt20-pre","format":{"id":"mtt20","title":"Tournament · 20bb (ante)","short":"MTT 20bb","summary":"Late-stage tournament: 20bb effective, 2x opens, 1bb big-blind ante, low SPR. Chip EV (no ICM)."},"phase":"preflop","title":"MTT 20bb pre","suites":["mtt20-preflop","mtt20-preflop-2"],"hands":170},{"key":"mtt20-post","format":{"id":"mtt20","title":"Tournament · 20bb (ante)","short":"MTT 20bb","summary":"Late-stage tournament: 20bb effective, 2x opens, 1bb big-blind ante, low SPR. Chip EV (no ICM)."},"phase":"postflop","title":"MTT 20bb post","suites":["mtt20-hands"],"hands":60},{"key":"spin-pre","format":{"id":"spin","title":"Spin & Go · 15–25bb","short":"Spin & Go","summary":"Hyper-turbo 3-max Spin & Go: 25bb 3-handed and 15bb heads-up, min-raises, very wide ranges. Chip EV."},"phase":"preflop","title":"Spin & Go pre","suites":["spin-preflop","spin-preflop-2"],"hands":220},{"key":"spin-post","format":{"id":"spin","title":"Spin & Go · 15–25bb","short":"Spin & Go","summary":"Hyper-turbo 3-max Spin & Go: 25bb 3-handed and 15bb heads-up, min-raises, very wide ranges. Chip EV."},"phase":"postflop","title":"Spin & Go post","suites":["spin-hands"],"hands":60}],"rows":[{"label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","cells":{"cash-pre":{"n":300,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"suites":["cash-preflop"]},"cash-post":{"n":120,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"suites":["cash-hands"]},"mtt40-post":{"n":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"suites":["mtt40-hands"]},"mtt20-pre":{"n":50,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"suites":["mtt20-preflop"]},"mtt20-post":{"n":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"suites":["mtt20-hands"]},"spin-pre":{"n":220,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"suites":["spin-preflop","spin-preflop-2"]},"spin-post":{"n":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"suites":["spin-hands"]}}},{"label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","cells":{"cash-pre":{"n":300,"bb":22.42,"ci":10.58,"mixed":null,"mixedCI":null,"suites":["cash-preflop"]},"cash-post":{"n":120,"bb":337.67,"ci":95.3,"mixed":null,"mixedCI":null,"suites":["cash-hands"]},"mtt40-post":{"n":60,"bb":188.04,"ci":53.33,"mixed":null,"mixedCI":null,"suites":["mtt40-hands"]},"mtt20-pre":{"n":50,"bb":81.81,"ci":29.94,"mixed":null,"mixedCI":null,"suites":["mtt20-preflop"]},"mtt20-post":{"n":60,"bb":106.84,"ci":34.81,"mixed":null,"mixedCI":null,"suites":["mtt20-hands"]},"spin-pre":{"n":220,"bb":40.4,"ci":9.68,"mixed":null,"mixedCI":null,"suites":["spin-preflop","spin-preflop-2"]},"spin-post":{"n":60,"bb":85.01,"ci":19.42,"mixed":null,"mixedCI":null,"suites":["spin-hands"]}}},{"label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","cells":{"cash-pre":{"n":300,"bb":0.04,"ci":0.02,"mixed":0.04,"mixedCI":0.01,"suites":["cash-preflop"]},"cash-post":{"n":120,"bb":8.47,"ci":8.9,"mixed":8.34,"mixedCI":8.88,"suites":["cash-hands"]},"mtt40-post":{"n":60,"bb":2.43,"ci":1.28,"mixed":3.48,"mixedCI":1.07,"suites":["mtt40-hands"]},"mtt20-pre":{"n":50,"bb":0.02,"ci":0.03,"mixed":0.03,"mixedCI":0.03,"suites":["mtt20-preflop"]},"mtt20-post":{"n":60,"bb":4.08,"ci":2.64,"mixed":3.7,"mixedCI":1.93,"suites":["mtt20-hands"]},"spin-pre":{"n":220,"bb":0.12,"ci":0.08,"mixed":0.13,"mixedCI":0.07,"suites":["spin-preflop","spin-preflop-2"]},"spin-post":{"n":60,"bb":1.22,"ci":0.79,"mixed":1.41,"mixedCI":0.53,"suites":["spin-hands"]}}},{"label":"Luna ensemble (eqrange+nuts)","name":"Luna ensemble (eqrange+nuts)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--nuts-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__nuts"]},"cells":{"cash-post":{"n":120,"bb":136.06,"ci":71.16,"mixed":155.97,"mixedCI":70.13,"suites":["cash-hands-dev","cash-hands-test"]}}},{"label":"Luna self-ensemble (5 variants)","name":"Luna self-ensemble (5 variants)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--eq--gpt-6-luna-decisions--multi--gpt-6-luna-decisions--v2--gpt-6-luna-decisions--noul-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eq","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__noul"]},"cells":{"cash-post":{"n":60,"bb":138.01,"ci":99.63,"mixed":198.61,"mixedCI":91.23,"suites":["cash-hands-dev"]}}},{"label":"Luna self-ensemble (eqrange+multi)","name":"Luna self-ensemble (eqrange+multi)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--multi-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi"]},"cells":{"cash-post":{"n":60,"bb":128.7,"ci":108.43,"mixed":187.38,"mixedCI":101.41,"suites":["cash-hands-dev"]}}},{"label":"Luna self-ensemble (eqrange+v2+multi)","name":"Luna self-ensemble (eqrange+v2+multi)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--v2--gpt-6-luna-decisions--multi-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi"]},"cells":{"cash-post":{"n":60,"bb":161.88,"ci":110.82,"mixed":193.32,"mixedCI":100.06,"suites":["cash-hands-dev"]}}},{"label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","cells":{"cash-pre":{"n":300,"bb":78.4,"ci":11.64,"mixed":null,"mixedCI":null,"suites":["cash-preflop"]},"cash-post":{"n":120,"bb":545.71,"ci":120.91,"mixed":null,"mixedCI":null,"suites":["cash-hands"]},"mtt40-post":{"n":60,"bb":457.32,"ci":137.42,"mixed":null,"mixedCI":null,"suites":["mtt40-hands"]},"mtt20-pre":{"n":50,"bb":77.87,"ci":22.65,"mixed":null,"mixedCI":null,"suites":["mtt20-preflop"]},"mtt20-post":{"n":60,"bb":256.54,"ci":97.48,"mixed":null,"mixedCI":null,"suites":["mtt20-hands"]},"spin-pre":{"n":220,"bb":51.23,"ci":8.52,"mixed":null,"mixedCI":null,"suites":["spin-preflop","spin-preflop-2"]},"spin-post":{"n":60,"bb":152.77,"ci":26.58,"mixed":null,"mixedCI":null,"suites":["spin-hands"]}}},{"label":"cloudflare/clef [nuts]","name":"Cloudflare Clef [nuts]","kind":"decisionModel","model":"cloudflare/clef","modelName":"Cloudflare Clef","variant":"nuts","cells":{"cash-post":{"n":60,"bb":133.95,"ci":89.07,"mixed":304.65,"mixedCI":85.67,"suites":["cash-hands-test"]},"mtt20-post":{"n":60,"bb":33.69,"ci":12.33,"mixed":108.1,"mixedCI":18.13,"suites":["mtt20-hands"]}}},{"label":"cloudflare/clef [v2]","name":"Cloudflare Clef","kind":"decisionModel","model":"cloudflare/clef","modelName":"Cloudflare Clef","variant":"v2","cells":{"cash-post":{"n":60,"bb":274.01,"ci":132.13,"mixed":470.21,"mixedCI":128.39,"suites":["cash-hands-test"]},"mtt20-post":{"n":60,"bb":80.22,"ci":36.42,"mixed":161.83,"mixedCI":33.16,"suites":["mtt20-hands"]}}},{"label":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +0%) [hybrid]","name":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +0%) [hybrid]","kind":"derived","model":"derived:guard-narrowed0-gpt-6-luna-decisions--eqrange-","derived":{"method":"guardrail","description":"HYBRID (not a pure model): fold probability moved to call when heuristic equity vs the villain's narrowed range ≥ price + 0%.","hybrid":true,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"cells":{"cash-post":{"n":60,"bb":146.55,"ci":139.79,"mixed":154.39,"mixedCI":111.7,"suites":["cash-hands-dev"]}}},{"label":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +5%) [hybrid]","name":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +5%) [hybrid]","kind":"derived","model":"derived:guard-narrowed5-gpt-6-luna-decisions--eqrange-","derived":{"method":"guardrail","description":"HYBRID (not a pure model): fold probability moved to call when heuristic equity vs the villain's narrowed range ≥ price + 5%.","hybrid":true,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"cells":{"cash-post":{"n":60,"bb":146.55,"ci":139.79,"mixed":154.43,"mixedCI":111.71,"suites":["cash-hands-dev"]}}},{"label":"gpt-6-luna-decisions [eqrange] τ=2","name":"gpt-6-luna-decisions [eqrange] τ=2","kind":"derived","model":"derived:temper2-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = 2 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"cells":{"cash-post":{"n":60,"bb":146.55,"ci":139.79,"mixed":146.31,"mixedCI":122.32,"suites":["cash-hands-dev"]}}},{"label":"gpt-6-luna-decisions [eqrange] τ=4","name":"gpt-6-luna-decisions [eqrange] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"cells":{"cash-post":{"n":120,"bb":146.4,"ci":83.82,"mixed":144.25,"mixedCI":76.93,"suites":["cash-hands-dev","cash-hands-test"]}}},{"label":"gpt-6-luna-decisions [eqrange] τ=inf","name":"gpt-6-luna-decisions [eqrange] τ=inf","kind":"derived","model":"derived:temperinf-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = inf and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"cells":{"cash-post":{"n":60,"bb":146.55,"ci":139.79,"mixed":144.99,"mixedCI":139.82,"suites":["cash-hands-dev"]}}},{"label":"gpt-6-luna-decisions [multi] τ=4","name":"gpt-6-luna-decisions [multi] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--multi-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-test__openai_gpt-6-luna-decisions__multi"]},"cells":{"cash-post":{"n":60,"bb":183.8,"ci":95.04,"mixed":199.96,"mixedCI":96.21,"suites":["cash-hands-test"]}}},{"label":"gpt-6-luna-decisions [nuts] τ=4","name":"gpt-6-luna-decisions [nuts] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--nuts-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__nuts"]},"cells":{"cash-post":{"n":120,"bb":130.94,"ci":71.01,"mixed":135.57,"mixedCI":70.77,"suites":["cash-hands-dev","cash-hands-test"]}}},{"label":"gpt-6-luna-decisions [v2] τ=2","name":"gpt-6-luna-decisions [v2] τ=2","kind":"derived","model":"derived:temper2-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = 2 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"cells":{"cash-post":{"n":60,"bb":155.95,"ci":100.59,"mixed":162.46,"mixedCI":80.73,"suites":["cash-hands-dev"]}}},{"label":"gpt-6-luna-decisions [v2] τ=4","name":"gpt-6-luna-decisions [v2] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"cells":{"cash-post":{"n":120,"bb":167.43,"ci":67.55,"mixed":167.58,"mixedCI":58.8,"suites":["cash-hands-dev","cash-hands-test"]}}},{"label":"gpt-6-luna-decisions [v2] τ=inf","name":"gpt-6-luna-decisions [v2] τ=inf","kind":"derived","model":"derived:temperinf-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = inf and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"cells":{"cash-post":{"n":60,"bb":155.95,"ci":100.59,"mixed":155.95,"mixedCI":100.59,"suites":["cash-hands-dev"]}}},{"label":"inception/mercury-decide [nuts]","name":"Inception Mercury Decide [nuts]","kind":"decisionModel","model":"inception/mercury-decide","modelName":"Inception Mercury Decide","variant":"nuts","cells":{"mtt20-post":{"n":60,"bb":43.85,"ci":19.99,"mixed":57.43,"mixedCI":16.53,"suites":["mtt20-hands"]}}},{"label":"inception/mercury-decide [v2]","name":"Inception Mercury Decide","kind":"decisionModel","model":"inception/mercury-decide","modelName":"Inception Mercury Decide","variant":"v2","cells":{"cash-post":{"n":35,"bb":243.12,"ci":123.46,"mixed":296.44,"mixedCI":137.83,"suites":["cash-hands-dev"]},"mtt20-post":{"n":60,"bb":82.68,"ci":31.86,"mixed":109.55,"mixedCI":31.07,"suites":["mtt20-hands"]}}},{"label":"inception/mercury-decide:free [nuts]","name":"Inception Mercury Decide (free endpoint) [nuts]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"nuts","cells":{"cash-post":{"n":120,"bb":107.63,"ci":50.19,"mixed":136.99,"mixedCI":47.5,"suites":["cash-hands-dev","cash-hands-test"]},"mtt40-post":{"n":60,"bb":73.7,"ci":34.79,"mixed":85.7,"mixedCI":32.45,"suites":["mtt40-hands"]},"mtt20-post":{"n":60,"bb":44.66,"ci":20.11,"mixed":57.44,"mixedCI":16.57,"suites":["mtt20-hands"]},"spin-post":{"n":60,"bb":36.15,"ci":15.17,"mixed":49.56,"mixedCI":12.55,"suites":["spin-hands"]}}},{"label":"inception/mercury-decide:free [sizing]","name":"Inception Mercury Decide (free endpoint) [sizing]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"sizing","cells":{"cash-post":{"n":120,"bb":130.34,"ci":56.9,"mixed":145.45,"mixedCI":49.78,"suites":["cash-hands-dev","cash-hands-test"]},"mtt40-post":{"n":60,"bb":78.7,"ci":35.7,"mixed":87.82,"mixedCI":32.98,"suites":["mtt40-hands"]},"mtt20-post":{"n":60,"bb":48.76,"ci":19.33,"mixed":62.58,"mixedCI":16.53,"suites":["mtt20-hands"]},"spin-post":{"n":60,"bb":37.29,"ci":13.65,"mixed":50.5,"mixedCI":12.31,"suites":["spin-hands"]}}},{"label":"inception/mercury-decide:free [v2]","name":"Inception Mercury Decide (free endpoint)","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"v2","cells":{"cash-post":{"n":120,"bb":244.68,"ci":85.25,"mixed":285.11,"mixedCI":72.32,"suites":["cash-hands-dev","cash-hands-test"]},"mtt40-post":{"n":60,"bb":100.21,"ci":43.66,"mixed":135.96,"mixedCI":34.86,"suites":["mtt40-hands"]},"mtt20-post":{"n":60,"bb":84.58,"ci":31.65,"mixed":109.53,"mixedCI":30.81,"suites":["mtt20-hands"]},"spin-post":{"n":60,"bb":50.32,"ci":15.42,"mixed":72.12,"mixedCI":12.76,"suites":["spin-hands"]}}},{"label":"liquid/d1 [nuts]","name":"Liquid d1 [nuts]","kind":"decisionModel","model":"liquid/d1","modelName":"Liquid d1","variant":"nuts","cells":{"mtt20-post":{"n":60,"bb":35.9,"ci":16.4,"mixed":48.03,"mixedCI":14.21,"suites":["mtt20-hands"]}}},{"label":"liquid/d1 [v2]","name":"Liquid d1","kind":"decisionModel","model":"liquid/d1","modelName":"Liquid d1","variant":"v2","cells":{"cash-post":{"n":35,"bb":198.81,"ci":182.23,"mixed":251.67,"mixedCI":152.44,"suites":["cash-hands-dev"]},"mtt20-post":{"n":60,"bb":58.98,"ci":34.59,"mixed":76.35,"mixedCI":24.47,"suites":["mtt20-hands"]}}},{"label":"openai/gpt-6-luna-decisions [coach]","name":"GPT-6 Luna Decisions [coach]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"coach","cells":{"cash-post":{"n":60,"bb":213.02,"ci":135.34,"mixed":251.28,"mixedCI":106.92,"suites":["cash-hands-dev"]},"mtt20-pre":{"n":50,"bb":44.27,"ci":8.24,"mixed":55.6,"mixedCI":9.34,"suites":["mtt20-preflop"]},"spin-pre":{"n":100,"bb":25.76,"ci":4.66,"mixed":30.38,"mixedCI":3.52,"suites":["spin-preflop"]}}},{"label":"openai/gpt-6-luna-decisions [eq]","name":"GPT-6 Luna Decisions [eq]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eq","cells":{"cash-post":{"n":60,"bb":167.14,"ci":108.92,"mixed":186.82,"mixedCI":98.35,"suites":["cash-hands-dev"]},"mtt20-pre":{"n":50,"bb":43.4,"ci":11.72,"mixed":46.11,"mixedCI":8.82,"suites":["mtt20-preflop"]},"spin-pre":{"n":100,"bb":27.2,"ci":5.68,"mixed":30.91,"mixedCI":4.43,"suites":["spin-preflop"]}}},{"label":"openai/gpt-6-luna-decisions [eqrange]","name":"GPT-6 Luna Decisions [eqrange]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eqrange","cells":{"cash-post":{"n":120,"bb":146.4,"ci":83.82,"mixed":158.55,"mixedCI":70.97,"suites":["cash-hands-dev","cash-hands-test"]}}},{"label":"openai/gpt-6-luna-decisions [minimal]","name":"GPT-6 Luna Decisions [minimal]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"minimal","cells":{"cash-post":{"n":60,"bb":231.3,"ci":106.6,"mixed":257.33,"mixedCI":113.54,"suites":["cash-hands-dev"]}}},{"label":"openai/gpt-6-luna-decisions [multi]","name":"GPT-6 Luna Decisions [multi]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"multi","cells":{"cash-post":{"n":120,"bb":165.75,"ci":68.88,"mixed":247.16,"mixedCI":69.24,"suites":["cash-hands-dev","cash-hands-test"]}}},{"label":"openai/gpt-6-luna-decisions [noul]","name":"GPT-6 Luna Decisions [noul]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"noul","cells":{"cash-post":{"n":60,"bb":150.68,"ci":54.76,"mixed":242.04,"mixedCI":75.89,"suites":["cash-hands-dev"]}}},{"label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","cells":{"cash-pre":{"n":140,"bb":20.69,"ci":14.07,"mixed":23.44,"mixedCI":16.58,"suites":["cash-preflop"]},"cash-post":{"n":120,"bb":130.94,"ci":71.01,"mixed":153.39,"mixedCI":69.62,"suites":["cash-hands-dev","cash-hands-test"]},"mtt40-post":{"n":60,"bb":55.08,"ci":32.01,"mixed":67.88,"mixedCI":31.5,"suites":["mtt40-hands"]},"mtt20-pre":{"n":50,"bb":36.71,"ci":8.24,"mixed":36.74,"mixedCI":7.2,"suites":["mtt20-preflop"]},"mtt20-post":{"n":60,"bb":39.73,"ci":18.55,"mixed":47.47,"mixedCI":17.49,"suites":["mtt20-hands"]},"spin-pre":{"n":100,"bb":19.9,"ci":4.21,"mixed":22.59,"mixedCI":3.35,"suites":["spin-preflop"]},"spin-post":{"n":60,"bb":28.32,"ci":13.06,"mixed":40.57,"mixedCI":13.14,"suites":["spin-hands"]}}},{"label":"openai/gpt-6-luna-decisions [shortstack]","name":"GPT-6 Luna Decisions [shortstack]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"shortstack","cells":{"mtt20-pre":{"n":50,"bb":27.11,"ci":15.82,"mixed":27.44,"mixedCI":14.87,"suites":["mtt20-preflop"]},"spin-pre":{"n":220,"bb":13.79,"ci":5.5,"mixed":15.25,"mixedCI":3.66,"suites":["spin-preflop","spin-preflop-2"]}}},{"label":"openai/gpt-6-luna-decisions [sizing]","name":"GPT-6 Luna Decisions [sizing]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"sizing","cells":{"cash-post":{"n":120,"bb":131.94,"ci":71.06,"mixed":155.28,"mixedCI":63.59,"suites":["cash-hands-dev","cash-hands-test"]}}},{"label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","cells":{"cash-pre":{"n":140,"bb":9.08,"ci":2.37,"mixed":15.97,"mixedCI":4.93,"suites":["cash-preflop"]},"cash-post":{"n":120,"bb":167.43,"ci":67.55,"mixed":241.04,"mixedCI":72.1,"suites":["cash-hands-dev","cash-hands-test"]},"mtt40-post":{"n":60,"bb":88.59,"ci":47.03,"mixed":141.55,"mixedCI":58.21,"suites":["mtt40-hands"]},"mtt20-pre":{"n":50,"bb":36.88,"ci":15.14,"mixed":48.3,"mixedCI":14.59,"suites":["mtt20-preflop"]},"mtt20-post":{"n":60,"bb":56.43,"ci":21.01,"mixed":88.2,"mixedCI":29.79,"suites":["mtt20-hands"]},"spin-pre":{"n":220,"bb":21.81,"ci":4.78,"mixed":30.12,"mixedCI":3.54,"suites":["spin-preflop","spin-preflop-2"]},"spin-post":{"n":60,"bb":45.46,"ci":18.39,"mixed":61.95,"mixedCI":14.46,"suites":["spin-hands"]}}},{"label":"typesafe/jev-1.13 [nuts]","name":"TypeSafe Jev 1.13 [nuts]","kind":"decisionModel","model":"typesafe/jev-1.13","modelName":"TypeSafe Jev 1.13","variant":"nuts","cells":{"mtt20-post":{"n":60,"bb":46.25,"ci":17.34,"mixed":61.78,"mixedCI":13.83,"suites":["mtt20-hands"]}}},{"label":"typesafe/jev-1.13 [v2]","name":"TypeSafe Jev 1.13","kind":"decisionModel","model":"typesafe/jev-1.13","modelName":"TypeSafe Jev 1.13","variant":"v2","cells":{"cash-post":{"n":35,"bb":145.59,"ci":95.67,"mixed":284.17,"mixedCI":111.66,"suites":["cash-hands-dev"]},"mtt20-post":{"n":60,"bb":63.44,"ci":35.72,"mixed":114.87,"mixedCI":31.11,"suites":["mtt20-hands"]}}}]},"experiments":[{"root":"20261009-170429-hands120-cash-n661-s31","rootKey":"cash-hands","format":{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},"mode":"hands","focus":"openai/gpt-6-luna-decisions","focusName":"GPT-6 Luna Decisions","splits":[{"split":"dev","suite":"cash-hands-dev","id":"20261009-170429-hands120-cash-n661-s31-dev","hands":60,"decisions":337,"reference":"openai/gpt-6-luna-decisions [v2]"},{"split":"test","suite":"cash-hands-test","id":"20261009-170429-hands120-cash-n661-s31-test","hands":60,"decisions":324,"reference":"openai/gpt-6-luna-decisions [v2]"}],"rows":[{"label":"Best-EV oracle","name":"Best-EV oracle","kind":"baseline","model":"baseline:bestEV","modelName":"Best-EV oracle","baseline":"bestEV","summary":"Always picks the highest-EV action — the ceiling.","focus":false,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"score":100,"scoreCI":0,"lossPot":0,"cost":null,"isReference":false,"diff":{"bb":{"n":60,"mean":-155.95,"ci":100.59,"sig":true},"mixed":null,"score":{"n":337,"mean":16.56,"ci":3.82,"sig":true},"lossPot":{"n":337,"mean":-0.02888,"ci":0.01189,"sig":true}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":0,"ci":0,"mixed":null,"mixedCI":null,"score":100,"scoreCI":0,"lossPot":0,"cost":null,"isReference":false,"diff":{"bb":{"n":60,"mean":-178.92,"ci":90.95,"sig":true},"mixed":null,"score":{"n":324,"mean":14.26,"ci":3.62,"sig":true},"lossPot":{"n":324,"mean":-0.02193,"ci":0.00848,"sig":true}}}},{"label":"GTO (sampled)","name":"GTO (sampled)","kind":"baseline","model":"baseline:gto","modelName":"GTO (sampled)","baseline":"gto","summary":"Samples each action with its equilibrium frequency.","focus":false,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":4.55,"ci":3.33,"mixed":4.8,"mixedCI":3.05,"score":96.75,"scoreCI":1.81,"lossPot":0.00069,"cost":null,"isReference":false,"diff":{"bb":{"n":60,"mean":-151.39,"ci":100.54,"sig":true},"mixed":{"n":60,"mean":-200.4,"ci":98.06,"sig":true},"score":{"n":337,"mean":13.31,"ci":3.77,"sig":true},"lossPot":{"n":337,"mean":-0.0282,"ci":0.0119,"sig":true}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":12.4,"ci":17.5,"mixed":11.87,"mixedCI":17.53,"score":95.08,"scoreCI":2.24,"lossPot":0.00155,"cost":null,"isReference":false,"diff":{"bb":{"n":60,"mean":-166.52,"ci":90.07,"sig":true},"mixed":{"n":60,"mean":-265,"ci":102.54,"sig":true},"score":{"n":324,"mean":9.34,"ci":3.78,"sig":true},"lossPot":{"n":324,"mean":-0.02038,"ci":0.00834,"sig":true}}}},{"label":"Luna self-ensemble (eqrange+multi)","name":"Luna self-ensemble (eqrange+multi)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--multi-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":128.7,"ci":108.43,"mixed":187.38,"mixedCI":101.41,"score":85.21,"scoreCI":3.7,"lossPot":0.02236,"cost":0.0928,"isReference":false,"diff":{"bb":{"n":60,"mean":-27.24,"ci":53.01,"sig":false},"mixed":{"n":60,"mean":-17.83,"ci":21.43,"sig":false},"score":{"n":337,"mean":1.77,"ci":1.9,"sig":false},"lossPot":{"n":337,"mean":-0.00652,"ci":0.00799,"sig":false}}}},{"label":"openai/gpt-6-luna-decisions [multi]","name":"GPT-6 Luna Decisions [multi]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"multi","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":147.69,"ci":100.31,"mixed":218.4,"mixedCI":96.17,"score":85.05,"scoreCI":3.66,"lossPot":0.02714,"cost":0.05573,"isReference":false,"diff":{"bb":{"n":60,"mean":-8.25,"ci":11.23,"sig":false},"mixed":{"n":60,"mean":13.2,"ci":11.78,"sig":true},"score":{"n":337,"mean":1.6,"ci":1.55,"sig":true},"lossPot":{"n":337,"mean":-0.00174,"ci":0.00341,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":183.8,"ci":95.04,"mixed":275.92,"mixedCI":99.9,"score":85.81,"scoreCI":3.64,"lossPot":0.02219,"cost":0.05468,"isReference":false,"diff":{"bb":{"n":60,"mean":4.88,"ci":26.63,"sig":false},"mixed":{"n":60,"mean":-0.95,"ci":23.13,"sig":false},"score":{"n":324,"mean":0.06,"ci":1.67,"sig":false},"lossPot":{"n":324,"mean":0.00027,"ci":0.00546,"sig":false}}}},{"label":"openai/gpt-6-luna-decisions [eqrange]","name":"GPT-6 Luna Decisions [eqrange]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eqrange","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":146.55,"ci":139.79,"mixed":156.36,"mixedCI":112.78,"score":85,"scoreCI":3.74,"lossPot":0.02155,"cost":0.03707,"isReference":false,"diff":{"bb":{"n":60,"mean":-9.4,"ci":100.95,"sig":false},"mixed":{"n":60,"mean":-48.85,"ci":46.69,"sig":true},"score":{"n":337,"mean":1.55,"ci":2.96,"sig":false},"lossPot":{"n":337,"mean":-0.00733,"ci":0.00969,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":146.25,"ci":93.8,"mixed":160.74,"mixedCI":87.15,"score":85.33,"scoreCI":3.74,"lossPot":0.01589,"cost":0.03634,"isReference":false,"diff":{"bb":{"n":60,"mean":-32.67,"ci":41.8,"sig":false},"mixed":{"n":60,"mean":-116.13,"ci":62.49,"sig":true},"score":{"n":324,"mean":-0.41,"ci":2.61,"sig":false},"lossPot":{"n":324,"mean":-0.00604,"ci":0.00704,"sig":false}}}},{"label":"gpt-6-luna-decisions [eqrange] τ=2","name":"gpt-6-luna-decisions [eqrange] τ=2","kind":"derived","model":"derived:temper2-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = 2 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":146.55,"ci":139.79,"mixed":146.31,"mixedCI":122.32,"score":85,"scoreCI":3.74,"lossPot":0.02155,"cost":0.03707,"isReference":false,"diff":{"bb":{"n":60,"mean":-9.4,"ci":100.95,"sig":false},"mixed":{"n":60,"mean":-58.9,"ci":53.65,"sig":true},"score":{"n":337,"mean":1.55,"ci":2.96,"sig":false},"lossPot":{"n":337,"mean":-0.00733,"ci":0.00969,"sig":false}}}},{"label":"gpt-6-luna-decisions [eqrange] τ=4","name":"gpt-6-luna-decisions [eqrange] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":146.55,"ci":139.79,"mixed":141.11,"mixedCI":123.37,"score":85,"scoreCI":3.74,"lossPot":0.02155,"cost":0.03707,"isReference":false,"diff":{"bb":{"n":60,"mean":-9.4,"ci":100.95,"sig":false},"mixed":{"n":60,"mean":-64.09,"ci":55.56,"sig":true},"score":{"n":337,"mean":1.55,"ci":2.96,"sig":false},"lossPot":{"n":337,"mean":-0.00733,"ci":0.00969,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":146.25,"ci":93.8,"mixed":147.39,"mixedCI":93.01,"score":85.33,"scoreCI":3.74,"lossPot":0.01589,"cost":0.03634,"isReference":false,"diff":{"bb":{"n":60,"mean":-32.67,"ci":41.8,"sig":false},"mixed":{"n":60,"mean":-129.48,"ci":65.57,"sig":true},"score":{"n":324,"mean":-0.41,"ci":2.61,"sig":false},"lossPot":{"n":324,"mean":-0.00604,"ci":0.00704,"sig":false}}}},{"label":"gpt-6-luna-decisions [eqrange] τ=inf","name":"gpt-6-luna-decisions [eqrange] τ=inf","kind":"derived","model":"derived:temperinf-gpt-6-luna-decisions--eqrange-","derived":{"method":"temper","description":"Probabilities raised to τ = inf and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":146.55,"ci":139.79,"mixed":144.99,"mixedCI":139.82,"score":85,"scoreCI":3.74,"lossPot":0.02155,"cost":0.03707,"isReference":false,"diff":{"bb":{"n":60,"mean":-9.4,"ci":100.95,"sig":false},"mixed":{"n":60,"mean":-60.21,"ci":76.16,"sig":false},"score":{"n":337,"mean":1.55,"ci":2.96,"sig":false},"lossPot":{"n":337,"mean":-0.00733,"ci":0.00969,"sig":false}}}},{"label":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +0%) [hybrid]","name":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +0%) [hybrid]","kind":"derived","model":"derived:guard-narrowed0-gpt-6-luna-decisions--eqrange-","derived":{"method":"guardrail","description":"HYBRID (not a pure model): fold probability moved to call when heuristic equity vs the villain's narrowed range ≥ price + 0%.","hybrid":true,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":146.55,"ci":139.79,"mixed":154.39,"mixedCI":111.7,"score":85,"scoreCI":3.74,"lossPot":0.02155,"cost":0.03707,"isReference":false,"diff":{"bb":{"n":60,"mean":-9.4,"ci":100.95,"sig":false},"mixed":{"n":60,"mean":-50.81,"ci":47.28,"sig":true},"score":{"n":337,"mean":1.55,"ci":2.96,"sig":false},"lossPot":{"n":337,"mean":-0.00733,"ci":0.00969,"sig":false}}}},{"label":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +5%) [hybrid]","name":"gpt-6-luna-decisions [eqrange] +foldguard(narrowed +5%) [hybrid]","kind":"derived","model":"derived:guard-narrowed5-gpt-6-luna-decisions--eqrange-","derived":{"method":"guardrail","description":"HYBRID (not a pure model): fold probability moved to call when heuristic equity vs the villain's narrowed range ≥ price + 5%.","hybrid":true,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":146.55,"ci":139.79,"mixed":154.43,"mixedCI":111.71,"score":85,"scoreCI":3.74,"lossPot":0.02155,"cost":0.03707,"isReference":false,"diff":{"bb":{"n":60,"mean":-9.4,"ci":100.95,"sig":false},"mixed":{"n":60,"mean":-50.77,"ci":47.27,"sig":true},"score":{"n":337,"mean":1.55,"ci":2.96,"sig":false},"lossPot":{"n":337,"mean":-0.00733,"ci":0.00969,"sig":false}}}},{"label":"Luna ensemble (eqrange+nuts)","name":"Luna ensemble (eqrange+nuts)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--nuts-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__nuts"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":124.52,"ci":108.06,"mixed":152.41,"mixedCI":110.9,"score":84.69,"scoreCI":3.77,"lossPot":0.02267,"cost":0.07831,"isReference":false,"diff":{"bb":{"n":60,"mean":-31.43,"ci":53.88,"sig":false},"mixed":{"n":60,"mean":-52.8,"ci":42.8,"sig":true},"score":{"n":337,"mean":1.25,"ci":2.9,"sig":false},"lossPot":{"n":337,"mean":-0.00621,"ci":0.00934,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":147.6,"ci":93.46,"mixed":159.53,"mixedCI":86.83,"score":84.02,"scoreCI":3.87,"lossPot":0.01584,"cost":0.0767,"isReference":false,"diff":{"bb":{"n":60,"mean":-31.32,"ci":41.72,"sig":false},"mixed":{"n":60,"mean":-117.34,"ci":62.84,"sig":true},"score":{"n":324,"mean":-1.72,"ci":2.47,"sig":false},"lossPot":{"n":324,"mean":-0.00608,"ci":0.00655,"sig":false}}}},{"label":"openai/gpt-6-luna-decisions [coach]","name":"GPT-6 Luna Decisions [coach]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"coach","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":213.02,"ci":135.34,"mixed":251.28,"mixedCI":106.92,"score":84.67,"scoreCI":3.68,"lossPot":0.03294,"cost":0.03086,"isReference":false,"diff":{"bb":{"n":60,"mean":57.08,"ci":60.35,"sig":false},"mixed":{"n":60,"mean":46.08,"ci":23.46,"sig":true},"score":{"n":337,"mean":1.23,"ci":2.93,"sig":false},"lossPot":{"n":337,"mean":0.00406,"ci":0.00869,"sig":false}}}},{"label":"Luna self-ensemble (5 variants)","name":"Luna self-ensemble (5 variants)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--eq--gpt-6-luna-decisions--multi--gpt-6-luna-decisions--v2--gpt-6-luna-decisions--noul-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eq","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__noul"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":138.01,"ci":99.63,"mixed":198.61,"mixedCI":91.23,"score":84.65,"scoreCI":3.72,"lossPot":0.02596,"cost":0.20407,"isReference":false,"diff":{"bb":{"n":60,"mean":-17.93,"ci":19.23,"sig":false},"mixed":{"n":60,"mean":-6.6,"ci":14.26,"sig":false},"score":{"n":337,"mean":1.21,"ci":1.07,"sig":true},"lossPot":{"n":337,"mean":-0.00292,"ci":0.003,"sig":false}}}},{"label":"Luna self-ensemble (eqrange+v2+multi)","name":"Luna self-ensemble (eqrange+v2+multi)","kind":"derived","model":"derived:ens-gpt-6-luna-decisions--eqrange--gpt-6-luna-decisions--v2--gpt-6-luna-decisions--multi-","derived":{"method":"ensemble","description":"Average of the members' action probabilities; argmax of the average is the action.","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__eqrange","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions","20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__multi"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":161.88,"ci":110.82,"mixed":193.32,"mixedCI":100.06,"score":84.39,"scoreCI":3.72,"lossPot":0.02868,"cost":0.12399,"isReference":false,"diff":{"bb":{"n":60,"mean":5.93,"ci":43.87,"sig":false},"mixed":{"n":60,"mean":-11.88,"ci":14.29,"sig":false},"score":{"n":337,"mean":0.95,"ci":1.09,"sig":false},"lossPot":{"n":337,"mean":-0.00021,"ci":0.00571,"sig":false}}}},{"label":"openai/gpt-6-luna-decisions [nuts]","name":"GPT-6 Luna Decisions [nuts]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"nuts","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":120.16,"ci":107.76,"mixed":148.46,"mixedCI":109.75,"score":84.39,"scoreCI":3.8,"lossPot":0.02239,"cost":0.04124,"isReference":false,"diff":{"bb":{"n":60,"mean":-35.78,"ci":54.45,"sig":false},"mixed":{"n":60,"mean":-56.75,"ci":40.65,"sig":true},"score":{"n":337,"mean":0.95,"ci":2.96,"sig":false},"lossPot":{"n":337,"mean":-0.00649,"ci":0.00937,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":141.71,"ci":93.36,"mixed":158.33,"mixedCI":86.63,"score":84.28,"scoreCI":3.85,"lossPot":0.01523,"cost":0.04036,"isReference":false,"diff":{"bb":{"n":60,"mean":-37.21,"ci":39.88,"sig":false},"mixed":{"n":60,"mean":-118.54,"ci":63.35,"sig":true},"score":{"n":324,"mean":-1.46,"ci":2.42,"sig":false},"lossPot":{"n":324,"mean":-0.00669,"ci":0.00645,"sig":true}}}},{"label":"gpt-6-luna-decisions [nuts] τ=4","name":"gpt-6-luna-decisions [nuts] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--nuts-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions__nuts"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":120.16,"ci":107.76,"mixed":125.9,"mixedCI":108.11,"score":84.39,"scoreCI":3.8,"lossPot":0.02239,"cost":0.04124,"isReference":false,"diff":{"bb":{"n":60,"mean":-35.78,"ci":54.45,"sig":false},"mixed":{"n":60,"mean":-79.31,"ci":40.55,"sig":true},"score":{"n":337,"mean":0.95,"ci":2.96,"sig":false},"lossPot":{"n":337,"mean":-0.00649,"ci":0.00937,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":141.71,"ci":93.36,"mixed":145.25,"mixedCI":92.21,"score":84.28,"scoreCI":3.85,"lossPot":0.01523,"cost":0.04036,"isReference":false,"diff":{"bb":{"n":60,"mean":-37.21,"ci":39.88,"sig":false},"mixed":{"n":60,"mean":-131.62,"ci":65.41,"sig":true},"score":{"n":324,"mean":-1.46,"ci":2.42,"sig":false},"lossPot":{"n":324,"mean":-0.00669,"ci":0.00645,"sig":true}}}},{"label":"openai/gpt-6-luna-decisions [eq]","name":"GPT-6 Luna Decisions [eq]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"eq","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":167.14,"ci":108.92,"mixed":186.82,"mixedCI":98.35,"score":84.22,"scoreCI":3.71,"lossPot":0.0311,"cost":0.035,"isReference":false,"diff":{"bb":{"n":60,"mean":11.19,"ci":53.91,"sig":false},"mixed":{"n":60,"mean":-18.38,"ci":31.84,"sig":false},"score":{"n":337,"mean":0.78,"ci":2.41,"sig":false},"lossPot":{"n":337,"mean":0.00222,"ci":0.00854,"sig":false}}}},{"label":"liquid/d1 [v2]","name":"Liquid d1","kind":"decisionModel","model":"liquid/d1","modelName":"Liquid d1","variant":"v2","focus":false,"confirmed":false,"dev":{"answered":200,"total":337,"complete":false,"hands":35,"bb":198.81,"ci":182.23,"mixed":251.67,"mixedCI":152.44,"score":84.19,"scoreCI":4.82,"lossPot":0.03143,"cost":0.00883,"isReference":false,"diff":{"bb":{"n":35,"mean":-1.53,"ci":79.78,"sig":false},"mixed":{"n":35,"mean":-20.86,"ci":49.92,"sig":false},"score":{"n":200,"mean":1.6,"ci":5.15,"sig":false},"lossPot":{"n":200,"mean":-0.00059,"ci":0.01334,"sig":false}}}},{"label":"openai/gpt-6-luna-decisions [sizing]","name":"GPT-6 Luna Decisions [sizing]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"sizing","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":120.75,"ci":107.71,"mixed":138.42,"mixedCI":87.32,"score":84.08,"scoreCI":3.83,"lossPot":0.02275,"cost":0.04298,"isReference":false,"diff":{"bb":{"n":60,"mean":-35.19,"ci":54.32,"sig":false},"mixed":{"n":60,"mean":-66.79,"ci":35.2,"sig":true},"score":{"n":337,"mean":0.64,"ci":2.78,"sig":false},"lossPot":{"n":337,"mean":-0.00613,"ci":0.00948,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":143.13,"ci":93.53,"mixed":172.15,"mixedCI":92.99,"score":83.97,"scoreCI":3.89,"lossPot":0.01744,"cost":0.04222,"isReference":false,"diff":{"bb":{"n":60,"mean":-35.79,"ci":42.28,"sig":false},"mixed":{"n":60,"mean":-104.72,"ci":62.01,"sig":true},"score":{"n":324,"mean":-1.78,"ci":2.63,"sig":false},"lossPot":{"n":324,"mean":-0.00448,"ci":0.00733,"sig":false}}}},{"label":"openai/gpt-6-luna-decisions [v2]","name":"GPT-6 Luna Decisions","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"v2","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":155.95,"ci":100.59,"mixed":205.2,"mixedCI":98.87,"score":83.44,"scoreCI":3.82,"lossPot":0.02888,"cost":0.03119,"isReference":true,"diff":null},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":178.92,"ci":90.95,"mixed":276.87,"mixedCI":105.01,"score":85.74,"scoreCI":3.62,"lossPot":0.02193,"cost":0.03059,"isReference":true,"diff":null}},{"label":"gpt-6-luna-decisions [v2] τ=2","name":"gpt-6-luna-decisions [v2] τ=2","kind":"derived","model":"derived:temper2-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = 2 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":155.95,"ci":100.59,"mixed":162.46,"mixedCI":80.73,"score":83.44,"scoreCI":3.82,"lossPot":0.02888,"cost":0.03119,"isReference":false,"diff":{"bb":{"n":60,"mean":0,"ci":0,"sig":false},"mixed":{"n":60,"mean":-42.75,"ci":25.3,"sig":true},"score":{"n":337,"mean":0,"ci":0,"sig":false},"lossPot":{"n":337,"mean":0,"ci":0,"sig":false}}}},{"label":"gpt-6-luna-decisions [v2] τ=4","name":"gpt-6-luna-decisions [v2] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":155.95,"ci":100.59,"mixed":144.33,"mixedCI":75.59,"score":83.44,"scoreCI":3.82,"lossPot":0.02888,"cost":0.03119,"isReference":false,"diff":{"bb":{"n":60,"mean":0,"ci":0,"sig":false},"mixed":{"n":60,"mean":-60.88,"ci":39.38,"sig":true},"score":{"n":337,"mean":0,"ci":0,"sig":false},"lossPot":{"n":337,"mean":0,"ci":0,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":178.92,"ci":90.95,"mixed":190.82,"mixedCI":90.36,"score":85.74,"scoreCI":3.62,"lossPot":0.02193,"cost":0.03059,"isReference":false,"diff":{"bb":{"n":60,"mean":0,"ci":0,"sig":false},"mixed":{"n":60,"mean":-86.05,"ci":57.74,"sig":true},"score":{"n":324,"mean":0,"ci":0,"sig":false},"lossPot":{"n":324,"mean":0,"ci":0,"sig":false}}}},{"label":"gpt-6-luna-decisions [v2] τ=inf","name":"gpt-6-luna-decisions [v2] τ=inf","kind":"derived","model":"derived:temperinf-gpt-6-luna-decisions--v2-","derived":{"method":"temper","description":"Probabilities raised to τ = inf and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-dev__openai_gpt-6-luna-decisions"]},"focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":155.95,"ci":100.59,"mixed":155.95,"mixedCI":100.59,"score":83.44,"scoreCI":3.82,"lossPot":0.02888,"cost":0.03119,"isReference":false,"diff":{"bb":{"n":60,"mean":0,"ci":0,"sig":false},"mixed":{"n":60,"mean":-49.26,"ci":44.96,"sig":true},"score":{"n":337,"mean":0,"ci":0,"sig":false},"lossPot":{"n":337,"mean":0,"ci":0,"sig":false}}}},{"label":"openai/gpt-6-luna-decisions [noul]","name":"GPT-6 Luna Decisions [noul]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"noul","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":150.68,"ci":54.76,"mixed":242.04,"mixedCI":75.89,"score":83,"scoreCI":3.85,"lossPot":0.03327,"cost":0.04508,"isReference":false,"diff":{"bb":{"n":60,"mean":-5.27,"ci":97.83,"sig":false},"mixed":{"n":60,"mean":36.83,"ci":54.93,"sig":false},"score":{"n":337,"mean":-0.44,"ci":2.66,"sig":false},"lossPot":{"n":337,"mean":0.00439,"ci":0.01143,"sig":false}}}},{"label":"inception/mercury-decide:free [nuts]","name":"Inception Mercury Decide (free endpoint) [nuts]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"nuts","focus":false,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":61.76,"ci":29.67,"mixed":105.19,"mixedCI":39.75,"score":82.17,"scoreCI":4.01,"lossPot":0.01793,"cost":0,"isReference":false,"diff":{"bb":{"n":60,"mean":-94.18,"ci":95.21,"sig":false},"mixed":{"n":60,"mean":-100.02,"ci":76.56,"sig":true},"score":{"n":337,"mean":-1.27,"ci":3.9,"sig":false},"lossPot":{"n":337,"mean":-0.01095,"ci":0.01251,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":153.5,"ci":94.9,"mixed":168.78,"mixedCI":85.97,"score":82.96,"scoreCI":3.95,"lossPot":0.02276,"cost":0,"isReference":false,"diff":{"bb":{"n":60,"mean":-25.42,"ci":68.96,"sig":false},"mixed":{"n":60,"mean":-108.08,"ci":63.21,"sig":true},"score":{"n":324,"mean":-2.79,"ci":4.23,"sig":false},"lossPot":{"n":324,"mean":0.00083,"ci":0.0099,"sig":false}}}},{"label":"typesafe/jev-1.13 [v2]","name":"TypeSafe Jev 1.13","kind":"decisionModel","model":"typesafe/jev-1.13","modelName":"TypeSafe Jev 1.13","variant":"v2","focus":false,"confirmed":false,"dev":{"answered":205,"total":337,"complete":false,"hands":35,"bb":145.59,"ci":95.67,"mixed":284.17,"mixedCI":111.66,"score":81.96,"scoreCI":5.08,"lossPot":0.024,"cost":0.01181,"isReference":false,"diff":{"bb":{"n":35,"mean":-54.76,"ci":94.91,"sig":false},"mixed":{"n":35,"mean":11.64,"ci":71.23,"sig":false},"score":{"n":205,"mean":-1.06,"ci":5.48,"sig":false},"lossPot":{"n":205,"mean":-0.00724,"ci":0.01473,"sig":false}}}},{"label":"inception/mercury-decide:free [sizing]","name":"Inception Mercury Decide (free endpoint) [sizing]","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"sizing","focus":false,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":93.6,"ci":62.06,"mixed":112.29,"mixedCI":47.72,"score":81.85,"scoreCI":4.02,"lossPot":0.02134,"cost":0,"isReference":false,"diff":{"bb":{"n":60,"mean":-62.35,"ci":107.7,"sig":false},"mixed":{"n":60,"mean":-92.91,"ci":71.58,"sig":true},"score":{"n":337,"mean":-1.59,"ci":4.14,"sig":false},"lossPot":{"n":337,"mean":-0.00754,"ci":0.01367,"sig":false}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":167.08,"ci":95.03,"mixed":178.61,"mixedCI":87.05,"score":81.99,"scoreCI":4,"lossPot":0.02649,"cost":0,"isReference":false,"diff":{"bb":{"n":60,"mean":-11.84,"ci":70.42,"sig":false},"mixed":{"n":60,"mean":-98.26,"ci":61.73,"sig":true},"score":{"n":324,"mean":-3.76,"ci":4.32,"sig":false},"lossPot":{"n":324,"mean":0.00457,"ci":0.01046,"sig":false}}}},{"label":"openai/gpt-6-luna-decisions [minimal]","name":"GPT-6 Luna Decisions [minimal]","kind":"decisionModel","model":"openai/gpt-6-luna-decisions","modelName":"GPT-6 Luna Decisions","variant":"minimal","focus":true,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":231.3,"ci":106.6,"mixed":257.33,"mixedCI":113.54,"score":80.42,"scoreCI":4.08,"lossPot":0.04131,"cost":0.0141,"isReference":false,"diff":{"bb":{"n":60,"mean":75.36,"ci":108,"sig":false},"mixed":{"n":60,"mean":52.12,"ci":37.39,"sig":true},"score":{"n":337,"mean":-3.02,"ci":3.36,"sig":false},"lossPot":{"n":337,"mean":0.01243,"ci":0.01411,"sig":false}}}},{"label":"Calling station","name":"Calling station","kind":"baseline","model":"baseline:callingStation","modelName":"Calling station","baseline":"callingStation","summary":"Checks or calls, never folds or raises.","focus":false,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":265.08,"ci":91.38,"mixed":null,"mixedCI":null,"score":79.47,"scoreCI":4.13,"lossPot":0.04809,"cost":null,"isReference":false,"diff":{"bb":{"n":60,"mean":109.14,"ci":103.8,"sig":true},"mixed":null,"score":{"n":337,"mean":-3.97,"ci":3.73,"sig":true},"lossPot":{"n":337,"mean":0.0192,"ci":0.01426,"sig":true}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":410.27,"ci":166.13,"mixed":null,"mixedCI":null,"score":80.08,"scoreCI":4.16,"lossPot":0.0423,"cost":null,"isReference":false,"diff":{"bb":{"n":60,"mean":231.35,"ci":137.47,"sig":true},"mixed":null,"score":{"n":324,"mean":-5.67,"ci":3.36,"sig":true},"lossPot":{"n":324,"mean":0.02037,"ci":0.00913,"sig":true}}}},{"label":"inception/mercury-decide:free [v2]","name":"Inception Mercury Decide (free endpoint)","kind":"decisionModel","model":"inception/mercury-decide:free","modelName":"Inception Mercury Decide (free endpoint)","variant":"v2","focus":false,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":219,"ci":113.09,"mixed":241.35,"mixedCI":89.76,"score":74.9,"scoreCI":4.41,"lossPot":0.0435,"cost":0,"isReference":false,"diff":{"bb":{"n":60,"mean":63.06,"ci":65.65,"sig":false},"mixed":{"n":60,"mean":36.15,"ci":39.96,"sig":false},"score":{"n":337,"mean":-8.54,"ci":5.04,"sig":true},"lossPot":{"n":337,"mean":0.01462,"ci":0.0117,"sig":true}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":270.35,"ci":128.22,"mixed":328.87,"mixedCI":113.11,"score":75.58,"scoreCI":4.4,"lossPot":0.04281,"cost":0,"isReference":false,"diff":{"bb":{"n":60,"mean":91.43,"ci":96.86,"sig":false},"mixed":{"n":60,"mean":52,"ci":77.27,"sig":false},"score":{"n":324,"mean":-10.16,"ci":4.96,"sig":true},"lossPot":{"n":324,"mean":0.02088,"ci":0.01177,"sig":true}}}},{"label":"inception/mercury-decide [v2]","name":"Inception Mercury Decide","kind":"decisionModel","model":"inception/mercury-decide","modelName":"Inception Mercury Decide","variant":"v2","focus":false,"confirmed":false,"dev":{"answered":200,"total":337,"complete":false,"hands":35,"bb":243.12,"ci":123.46,"mixed":296.44,"mixedCI":137.83,"score":74.64,"scoreCI":5.72,"lossPot":0.04612,"cost":0.00398,"isReference":false,"diff":{"bb":{"n":35,"mean":42.77,"ci":126.7,"sig":false},"mixed":{"n":35,"mean":23.9,"ci":54.75,"sig":false},"score":{"n":200,"mean":-7.95,"ci":6.69,"sig":true},"lossPot":{"n":200,"mean":0.0141,"ci":0.01899,"sig":false}}}},{"label":"Random","name":"Random","kind":"baseline","model":"baseline:random","modelName":"Random","baseline":"random","summary":"Picks a legal action uniformly at random.","focus":false,"confirmed":false,"dev":{"answered":337,"total":337,"complete":true,"hands":60,"bb":428.81,"ci":148.51,"mixed":null,"mixedCI":null,"score":62.7,"scoreCI":5.05,"lossPot":0.09346,"cost":null,"isReference":false,"diff":{"bb":{"n":60,"mean":272.86,"ci":178.19,"sig":true},"mixed":null,"score":{"n":337,"mean":-20.75,"ci":5.9,"sig":true},"lossPot":{"n":337,"mean":0.06458,"ci":0.02153,"sig":true}}},"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":662.61,"ci":187.45,"mixed":null,"mixedCI":null,"score":59.63,"scoreCI":5.11,"lossPot":0.09529,"cost":null,"isReference":false,"diff":{"bb":{"n":60,"mean":483.69,"ci":161.97,"sig":true},"mixed":null,"score":{"n":324,"mean":-26.12,"ci":5.81,"sig":true},"lossPot":{"n":324,"mean":0.07336,"ci":0.01745,"sig":true}}}},{"label":"gpt-6-luna-decisions [multi] τ=4","name":"gpt-6-luna-decisions [multi] τ=4","kind":"derived","model":"derived:temper4-gpt-6-luna-decisions--multi-","derived":{"method":"temper","description":"Probabilities raised to τ = 4 and renormalised (τ > 1 sharpens, < 1 flattens).","hybrid":false,"sources":["20261009-170429-hands120-cash-n661-s31-test__openai_gpt-6-luna-decisions__multi"]},"focus":true,"confirmed":false,"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":183.8,"ci":95.04,"mixed":199.96,"mixedCI":96.21,"score":85.81,"scoreCI":3.64,"lossPot":0.02219,"cost":0.05468,"isReference":false,"diff":{"bb":{"n":60,"mean":4.88,"ci":26.63,"sig":false},"mixed":{"n":60,"mean":-76.91,"ci":58.68,"sig":true},"score":{"n":324,"mean":0.06,"ci":1.67,"sig":false},"lossPot":{"n":324,"mean":0.00027,"ci":0.00546,"sig":false}}}},{"label":"cloudflare/clef [nuts]","name":"Cloudflare Clef [nuts]","kind":"decisionModel","model":"cloudflare/clef","modelName":"Cloudflare Clef","variant":"nuts","focus":false,"confirmed":false,"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":133.95,"ci":89.07,"mixed":304.65,"mixedCI":85.67,"score":85.27,"scoreCI":3.74,"lossPot":0.01691,"cost":0.10117,"isReference":false,"diff":{"bb":{"n":60,"mean":-44.97,"ci":58.49,"sig":false},"mixed":{"n":60,"mean":27.79,"ci":49.9,"sig":false},"score":{"n":324,"mean":-0.47,"ci":3.54,"sig":false},"lossPot":{"n":324,"mean":-0.00502,"ci":0.00886,"sig":false}}}},{"label":"cloudflare/clef [v2]","name":"Cloudflare Clef","kind":"decisionModel","model":"cloudflare/clef","modelName":"Cloudflare Clef","variant":"v2","focus":false,"confirmed":false,"test":{"answered":324,"total":324,"complete":true,"hands":60,"bb":274.01,"ci":132.13,"mixed":470.21,"mixedCI":128.39,"score":82.21,"scoreCI":3.94,"lossPot":0.03102,"cost":0.07719,"isReference":false,"diff":{"bb":{"n":60,"mean":95.09,"ci":104.07,"sig":false},"mixed":{"n":60,"mean":193.34,"ci":77.17,"sig":true},"score":{"n":324,"mean":-3.53,"ci":4.04,"sig":false},"lossPot":{"n":324,"mean":0.0091,"ci":0.00986,"sig":false}}}}]}],"formatInfo":[{"id":"cash","title":"Cash game · 100bb","short":"Cash 100bb","summary":"Deep-stacked cash games: 6-max, 100bb, 2.5x opens, no ante."},{"id":"mtt40","title":"Tournament · 40bb (ante)","short":"MTT 40bb","summary":"Mid-stage tournament: 40bb effective, 2.2x opens, 1bb big-blind ante. Chip EV (no ICM)."},{"id":"mtt20","title":"Tournament · 20bb (ante)","short":"MTT 20bb","summary":"Late-stage tournament: 20bb effective, 2x opens, 1bb big-blind ante, low SPR. Chip EV (no ICM)."},{"id":"spin","title":"Spin & Go · 15–25bb","short":"Spin & Go","summary":"Hyper-turbo 3-max Spin & Go: 25bb 3-handed and 15bb heads-up, min-raises, very wide ranges. Chip EV."}],"variants":[{"id":"v2","summary":"Default: full state with derived facts (made hand, draws, pot odds, SPR) + one choice question"},{"id":"minimal","summary":"Raw facts only (cards, positions, pot/stacks/to-call, history, actions); no derived facts"},{"id":"eq","summary":"v2 + hero equity and made-hand percentile vs villain's preflop range (Monte-Carlo), equity vs needed"},{"id":"eqrange","summary":"eq, but equity vs villain's range narrowed by its actions (strength heuristic, no solver data)"},{"id":"coach","summary":"v2 state; criteria rewritten as concise GTO theory (value/bluff/bluff-catch, MDF, polarisation)"},{"id":"multi","summary":"v2 state; 3 independently answered choice questions (v2 / coach / solver phrasing), probabilities averaged"},{"id":"noul","summary":"v2 state; one noul per action ('is <action> the highest-EV action?'), P(true) normalised"},{"id":"nuts","summary":"eqrange + exact nut ranking (holdings that beat hero now) + value-extraction guidance for strong hands"},{"id":"shortstack","summary":"v2 + short-stack preflop guidance (≤25bb: limp/call, fold or shove; small raises rarely best)"},{"id":"sizing","summary":"nuts + guidance on what each bet/raise size is for (small = thin value/protection, large = polarised)"}],"thresholds":{"handsMinDecisions":50,"preflopMinDecisions":100},"calibration":{"definition":"Decision-model answers with action probabilities, all stored suites/variants. Confidence = top probability; buckets lower-inclusive. Best = pick within 0.25% pot of the top EV.","focus":"openai/gpt-6-luna-decisions","edges":[0,0.4,0.6,0.8,1],"fineEdges":[0,0.4,0.5,0.6,0.7,0.8,0.9,1],"overall":{"n":19887,"meanTop":0.7635,"best":0.6989,"lossPot":0.03651,"ece":0.0948,"buckets":[{"lo":0,"hi":0.4,"n":316,"share":0.0159,"meanTop":0.3731,"best":0.3987,"bestCI":0.054,"lossPot":0.09852,"lossPotCI":0.01958},{"lo":0.4,"hi":0.6,"n":4079,"share":0.2051,"meanTop":0.519,"best":0.5761,"bestCI":0.0152,"lossPot":0.05712,"lossPotCI":0.00398},{"lo":0.6,"hi":0.8,"n":5910,"share":0.2972,"meanTop":0.7021,"best":0.6834,"bestCI":0.0119,"lossPot":0.03775,"lossPotCI":0.00265},{"lo":0.8,"hi":1,"n":9582,"share":0.4818,"meanTop":0.9183,"best":0.7707,"bestCI":0.0084,"lossPot":0.02493,"lossPotCI":0.00177}],"curve":[{"lo":0,"hi":0.4,"n":316,"share":0.0159,"meanTop":0.3731,"best":0.3987,"bestCI":0.054,"lossPot":0.09852,"lossPotCI":0.01958},{"lo":0.4,"hi":0.5,"n":1284,"share":0.0646,"meanTop":0.4542,"best":0.4696,"bestCI":0.0273,"lossPot":0.07428,"lossPotCI":0.00792},{"lo":0.5,"hi":0.6,"n":2795,"share":0.1405,"meanTop":0.5488,"best":0.625,"bestCI":0.0179,"lossPot":0.04923,"lossPotCI":0.00451},{"lo":0.6,"hi":0.7,"n":2726,"share":0.1371,"meanTop":0.6473,"best":0.6691,"bestCI":0.0177,"lossPot":0.03901,"lossPotCI":0.00388},{"lo":0.7,"hi":0.8,"n":3184,"share":0.1601,"meanTop":0.749,"best":0.6957,"bestCI":0.016,"lossPot":0.03668,"lossPotCI":0.00362},{"lo":0.8,"hi":0.9,"n":3642,"share":0.1831,"meanTop":0.8484,"best":0.7273,"bestCI":0.0145,"lossPot":0.02837,"lossPotCI":0.00285},{"lo":0.9,"hi":1,"n":5940,"share":0.2987,"meanTop":0.9612,"best":0.7973,"bestCI":0.0102,"lossPot":0.02283,"lossPotCI":0.00226}]},"models":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","n":9526,"meanTop":0.8127,"best":0.7265,"lossPot":0.04178,"ece":0.0973,"buckets":[{"lo":0,"hi":0.4,"n":28,"share":0.0029,"meanTop":0.3726,"best":0.3214,"bestCI":0.173,"lossPot":0.39888,"lossPotCI":0.14072},{"lo":0.4,"hi":0.6,"n":1143,"share":0.12,"meanTop":0.5364,"best":0.5372,"bestCI":0.0289,"lossPot":0.08611,"lossPotCI":0.00997},{"lo":0.6,"hi":0.8,"n":2754,"share":0.2891,"meanTop":0.701,"best":0.6924,"bestCI":0.0172,"lossPot":0.04666,"lossPotCI":0.00461},{"lo":0.8,"hi":1,"n":5601,"share":0.588,"meanTop":0.9262,"best":0.784,"bestCI":0.0108,"lossPot":0.02854,"lossPotCI":0.0026}],"curve":[{"lo":0,"hi":0.4,"n":28,"share":0.0029,"meanTop":0.3726,"best":0.3214,"bestCI":0.173,"lossPot":0.39888,"lossPotCI":0.14072},{"lo":0.4,"hi":0.5,"n":134,"share":0.0141,"meanTop":0.4549,"best":0.2836,"bestCI":0.0763,"lossPot":0.2382,"lossPotCI":0.04714},{"lo":0.5,"hi":0.6,"n":1009,"share":0.1059,"meanTop":0.5472,"best":0.5709,"bestCI":0.0305,"lossPot":0.06591,"lossPotCI":0.00868},{"lo":0.6,"hi":0.7,"n":1261,"share":0.1324,"meanTop":0.6462,"best":0.6693,"bestCI":0.026,"lossPot":0.04675,"lossPotCI":0.00659},{"lo":0.7,"hi":0.8,"n":1493,"share":0.1567,"meanTop":0.7474,"best":0.712,"bestCI":0.023,"lossPot":0.04658,"lossPotCI":0.00645},{"lo":0.8,"hi":0.9,"n":1814,"share":0.1904,"meanTop":0.848,"best":0.7514,"bestCI":0.0199,"lossPot":0.03407,"lossPotCI":0.0047},{"lo":0.9,"hi":1,"n":3787,"share":0.3975,"meanTop":0.9637,"best":0.7996,"bestCI":0.0128,"lossPot":0.0259,"lossPotCI":0.00312}]},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","n":5704,"meanTop":0.7981,"best":0.6978,"lossPot":0.02859,"ece":0.1209,"buckets":[{"lo":0,"hi":0.4,"n":8,"share":0.0014,"meanTop":0.3745,"best":0.375,"bestCI":0.3355,"lossPot":0.06874,"lossPotCI":0.05113},{"lo":0.4,"hi":0.6,"n":731,"share":0.1282,"meanTop":0.5368,"best":0.617,"bestCI":0.0352,"lossPot":0.04868,"lossPotCI":0.0086},{"lo":0.6,"hi":0.8,"n":1841,"share":0.3228,"meanTop":0.7161,"best":0.6638,"bestCI":0.0216,"lossPot":0.03081,"lossPotCI":0.00358},{"lo":0.8,"hi":1,"n":3124,"share":0.5477,"meanTop":0.9087,"best":0.7375,"bestCI":0.0154,"lossPot":0.02248,"lossPotCI":0.00262}],"curve":[{"lo":0,"hi":0.4,"n":8,"share":0.0014,"meanTop":0.3745,"best":0.375,"bestCI":0.3355,"lossPot":0.06874,"lossPotCI":0.05113},{"lo":0.4,"hi":0.5,"n":142,"share":0.0249,"meanTop":0.4714,"best":0.5282,"bestCI":0.0821,"lossPot":0.05393,"lossPotCI":0.01841},{"lo":0.5,"hi":0.6,"n":589,"share":0.1033,"meanTop":0.5526,"best":0.6384,"bestCI":0.0388,"lossPot":0.04741,"lossPotCI":0.00971},{"lo":0.6,"hi":0.7,"n":690,"share":0.121,"meanTop":0.6523,"best":0.6435,"bestCI":0.0357,"lossPot":0.03498,"lossPotCI":0.00643},{"lo":0.7,"hi":0.8,"n":1151,"share":0.2018,"meanTop":0.7543,"best":0.6759,"bestCI":0.027,"lossPot":0.02831,"lossPotCI":0.00423},{"lo":0.8,"hi":0.9,"n":1422,"share":0.2493,"meanTop":0.849,"best":0.6864,"bestCI":0.0241,"lossPot":0.02496,"lossPotCI":0.00375},{"lo":0.9,"hi":1,"n":1702,"share":0.2984,"meanTop":0.9586,"best":0.7803,"bestCI":0.0197,"lossPot":0.0204,"lossPotCI":0.00364}]},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef","n":1448,"meanTop":0.5519,"best":0.7265,"lossPot":0.02627,"ece":0.1769,"buckets":[{"lo":0,"hi":0.4,"n":146,"share":0.1008,"meanTop":0.3691,"best":0.4658,"bestCI":0.0809,"lossPot":0.06105,"lossPotCI":0.01715},{"lo":0.4,"hi":0.6,"n":879,"share":0.607,"meanTop":0.5072,"best":0.7235,"bestCI":0.0296,"lossPot":0.02553,"lossPotCI":0.0049},{"lo":0.6,"hi":0.8,"n":349,"share":0.241,"meanTop":0.6728,"best":0.8166,"bestCI":0.0406,"lossPot":0.01872,"lossPotCI":0.00759},{"lo":0.8,"hi":1,"n":74,"share":0.0511,"meanTop":0.8738,"best":0.8514,"bestCI":0.0811,"lossPot":0.00203,"lossPotCI":0.00153}],"curve":[{"lo":0,"hi":0.4,"n":146,"share":0.1008,"meanTop":0.3691,"best":0.4658,"bestCI":0.0809,"lossPot":0.06105,"lossPotCI":0.01715},{"lo":0.4,"hi":0.5,"n":372,"share":0.2569,"meanTop":0.4524,"best":0.6774,"bestCI":0.0475,"lossPot":0.03243,"lossPotCI":0.00814},{"lo":0.5,"hi":0.6,"n":507,"share":0.3501,"meanTop":0.5475,"best":0.7574,"bestCI":0.0373,"lossPot":0.02047,"lossPotCI":0.00601},{"lo":0.6,"hi":0.7,"n":244,"share":0.1685,"meanTop":0.6431,"best":0.8279,"bestCI":0.0474,"lossPot":0.01705,"lossPotCI":0.00848},{"lo":0.7,"hi":0.8,"n":105,"share":0.0725,"meanTop":0.7417,"best":0.7905,"bestCI":0.0778,"lossPot":0.0226,"lossPotCI":0.01579},{"lo":0.8,"hi":0.9,"n":50,"share":0.0345,"meanTop":0.8456,"best":0.84,"bestCI":0.1016,"lossPot":0.00234,"lossPotCI":0.00209},{"lo":0.9,"hi":1,"n":24,"share":0.0166,"meanTop":0.9327,"best":0.875,"bestCI":0.1323,"lossPot":0.00137,"lossPotCI":0.00184}]},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev","n":1009,"meanTop":0.6521,"best":0.6987,"lossPot":0.02539,"ece":0.0947,"buckets":[{"lo":0,"hi":0.4,"n":9,"share":0.0089,"meanTop":0.3644,"best":0.4444,"bestCI":0.3246,"lossPot":0.02458,"lossPotCI":0.03024},{"lo":0.4,"hi":0.6,"n":375,"share":0.3717,"meanTop":0.5196,"best":0.6587,"bestCI":0.048,"lossPot":0.03221,"lossPotCI":0.00858},{"lo":0.6,"hi":0.8,"n":467,"share":0.4628,"meanTop":0.685,"best":0.7002,"bestCI":0.0416,"lossPot":0.02526,"lossPotCI":0.00661},{"lo":0.8,"hi":1,"n":158,"share":0.1566,"meanTop":0.8857,"best":0.8038,"bestCI":0.0619,"lossPot":0.00965,"lossPotCI":0.00609}],"curve":[{"lo":0,"hi":0.4,"n":9,"share":0.0089,"meanTop":0.3644,"best":0.4444,"bestCI":0.3246,"lossPot":0.02458,"lossPotCI":0.03024},{"lo":0.4,"hi":0.5,"n":117,"share":0.116,"meanTop":0.4584,"best":0.5385,"bestCI":0.0903,"lossPot":0.05496,"lossPotCI":0.02159},{"lo":0.5,"hi":0.6,"n":258,"share":0.2557,"meanTop":0.5474,"best":0.7132,"bestCI":0.0552,"lossPot":0.02189,"lossPotCI":0.00743},{"lo":0.6,"hi":0.7,"n":260,"share":0.2577,"meanTop":0.6445,"best":0.7154,"bestCI":0.0548,"lossPot":0.02444,"lossPotCI":0.00781},{"lo":0.7,"hi":0.8,"n":207,"share":0.2052,"meanTop":0.7358,"best":0.6812,"bestCI":0.0635,"lossPot":0.02629,"lossPotCI":0.01125},{"lo":0.8,"hi":0.9,"n":93,"share":0.0922,"meanTop":0.8396,"best":0.7312,"bestCI":0.0901,"lossPot":0.0152,"lossPotCI":0.01015},{"lo":0.9,"hi":1,"n":65,"share":0.0644,"meanTop":0.9515,"best":0.9077,"bestCI":0.0704,"lossPot":0.00171,"lossPotCI":0.00165}]},{"model":"liquid/d1","name":"Liquid d1","short":"d1","n":1000,"meanTop":0.7968,"best":0.725,"lossPot":0.02425,"ece":0.0846,"buckets":[{"lo":0,"hi":0.4,"n":2,"share":0.002,"meanTop":0.3758,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":149,"share":0.149,"meanTop":0.5358,"best":0.5705,"bestCI":0.0795,"lossPot":0.05119,"lossPotCI":0.022},{"lo":0.6,"hi":0.8,"n":287,"share":0.287,"meanTop":0.7092,"best":0.6585,"bestCI":0.0549,"lossPot":0.0354,"lossPotCI":0.01217},{"lo":0.8,"hi":1,"n":562,"share":0.562,"meanTop":0.9122,"best":0.7989,"bestCI":0.0331,"lossPot":0.0115,"lossPotCI":0.00435}],"curve":[{"lo":0,"hi":0.4,"n":2,"share":0.002,"meanTop":0.3758,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":34,"share":0.034,"meanTop":0.4622,"best":0.5,"bestCI":0.1681,"lossPot":0.0383,"lossPotCI":0.02034},{"lo":0.5,"hi":0.6,"n":115,"share":0.115,"meanTop":0.5576,"best":0.5913,"bestCI":0.0898,"lossPot":0.055,"lossPotCI":0.02786},{"lo":0.6,"hi":0.7,"n":121,"share":0.121,"meanTop":0.6537,"best":0.6281,"bestCI":0.0861,"lossPot":0.04376,"lossPotCI":0.02108},{"lo":0.7,"hi":0.8,"n":166,"share":0.166,"meanTop":0.7496,"best":0.6807,"bestCI":0.0709,"lossPot":0.02931,"lossPotCI":0.01436},{"lo":0.8,"hi":0.9,"n":225,"share":0.225,"meanTop":0.8529,"best":0.7556,"bestCI":0.0562,"lossPot":0.01734,"lossPotCI":0.00965},{"lo":0.9,"hi":1,"n":337,"share":0.337,"meanTop":0.9518,"best":0.8279,"bestCI":0.0403,"lossPot":0.0076,"lossPotCI":0.00327}]},{"model":"cloudflare/clef-flash","name":"Cloudflare Clef Flash","short":"Clef Flash","n":200,"meanTop":0.4534,"best":0.32,"lossPot":0.07741,"ece":0.1593,"buckets":[{"lo":0,"hi":0.4,"n":44,"share":0.22,"meanTop":0.3798,"best":0.25,"bestCI":0.1279,"lossPot":0.07779,"lossPotCI":0.02637},{"lo":0.4,"hi":0.6,"n":146,"share":0.73,"meanTop":0.4602,"best":0.3151,"bestCI":0.0754,"lossPot":0.08013,"lossPotCI":0.01626},{"lo":0.6,"hi":0.8,"n":10,"share":0.05,"meanTop":0.6775,"best":0.7,"bestCI":0.284,"lossPot":0.03598,"lossPotCI":0.06603},{"lo":0.8,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}],"curve":[{"lo":0,"hi":0.4,"n":44,"share":0.22,"meanTop":0.3798,"best":0.25,"bestCI":0.1279,"lossPot":0.07779,"lossPotCI":0.02637},{"lo":0.4,"hi":0.5,"n":116,"share":0.58,"meanTop":0.4403,"best":0.2414,"bestCI":0.0779,"lossPot":0.08674,"lossPotCI":0.01775},{"lo":0.5,"hi":0.6,"n":30,"share":0.15,"meanTop":0.5369,"best":0.6,"bestCI":0.1753,"lossPot":0.05458,"lossPotCI":0.03871},{"lo":0.6,"hi":0.7,"n":7,"share":0.035,"meanTop":0.6391,"best":0.5714,"bestCI":0.3666,"lossPot":0.0514,"lossPotCI":0.09399},{"lo":0.7,"hi":0.8,"n":3,"share":0.015,"meanTop":0.7671,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.8,"hi":0.9,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"jaredpalmer/kev-4b","name":"Kev 4B","short":"Kev","n":200,"meanTop":0.4499,"best":0.465,"lossPot":0.06263,"ece":0.0666,"buckets":[{"lo":0,"hi":0.4,"n":55,"share":0.275,"meanTop":0.3765,"best":0.3636,"bestCI":0.1271,"lossPot":0.08833,"lossPotCI":0.03257},{"lo":0.4,"hi":0.6,"n":135,"share":0.675,"meanTop":0.4668,"best":0.4815,"bestCI":0.0843,"lossPot":0.05641,"lossPotCI":0.01682},{"lo":0.6,"hi":0.8,"n":10,"share":0.05,"meanTop":0.6264,"best":0.8,"bestCI":0.2479,"lossPot":0.00535,"lossPotCI":0.0094},{"lo":0.8,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}],"curve":[{"lo":0,"hi":0.4,"n":55,"share":0.275,"meanTop":0.3765,"best":0.3636,"bestCI":0.1271,"lossPot":0.08833,"lossPotCI":0.03257},{"lo":0.4,"hi":0.5,"n":101,"share":0.505,"meanTop":0.44,"best":0.396,"bestCI":0.0954,"lossPot":0.06442,"lossPotCI":0.02032},{"lo":0.5,"hi":0.6,"n":34,"share":0.17,"meanTop":0.5462,"best":0.7353,"bestCI":0.1483,"lossPot":0.03261,"lossPotCI":0.02752},{"lo":0.6,"hi":0.7,"n":10,"share":0.05,"meanTop":0.6264,"best":0.8,"bestCI":0.2479,"lossPot":0.00535,"lossPotCI":0.0094},{"lo":0.7,"hi":0.8,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.8,"hi":0.9,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"perplexity/pplx-decider-v1.1-27b","name":"Perplexity Decider v1.1 27B","short":"Perplexity","n":200,"meanTop":0.6512,"best":0.58,"lossPot":0.03521,"ece":0.1038,"buckets":[{"lo":0,"hi":0.4,"n":9,"share":0.045,"meanTop":0.3805,"best":0.5556,"bestCI":0.3246,"lossPot":0.04316,"lossPotCI":0.05142},{"lo":0.4,"hi":0.6,"n":67,"share":0.335,"meanTop":0.5204,"best":0.4328,"bestCI":0.1186,"lossPot":0.0542,"lossPotCI":0.01996},{"lo":0.6,"hi":0.8,"n":88,"share":0.44,"meanTop":0.689,"best":0.5568,"bestCI":0.1038,"lossPot":0.03339,"lossPotCI":0.01272},{"lo":0.8,"hi":1,"n":36,"share":0.18,"meanTop":0.8697,"best":0.9167,"bestCI":0.0903,"lossPot":0.00231,"lossPotCI":0.00319}],"curve":[{"lo":0,"hi":0.4,"n":9,"share":0.045,"meanTop":0.3805,"best":0.5556,"bestCI":0.3246,"lossPot":0.04316,"lossPotCI":0.05142},{"lo":0.4,"hi":0.5,"n":25,"share":0.125,"meanTop":0.4584,"best":0.44,"bestCI":0.1946,"lossPot":0.06792,"lossPotCI":0.03423},{"lo":0.5,"hi":0.6,"n":42,"share":0.21,"meanTop":0.5573,"best":0.4286,"bestCI":0.1497,"lossPot":0.04604,"lossPotCI":0.02446},{"lo":0.6,"hi":0.7,"n":51,"share":0.255,"meanTop":0.6496,"best":0.5098,"bestCI":0.1372,"lossPot":0.04408,"lossPotCI":0.01947},{"lo":0.7,"hi":0.8,"n":37,"share":0.185,"meanTop":0.7432,"best":0.6216,"bestCI":0.1563,"lossPot":0.01866,"lossPotCI":0.0128},{"lo":0.8,"hi":0.9,"n":23,"share":0.115,"meanTop":0.8373,"best":0.8696,"bestCI":0.1376,"lossPot":0.00362,"lossPotCI":0.00494},{"lo":0.9,"hi":1,"n":13,"share":0.065,"meanTop":0.9272,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"togethercomputer/tev1-4b-experimental","name":"Together Tev1 4B (exp.)","short":"Tev1","n":200,"meanTop":0.5087,"best":0.325,"lossPot":0.07423,"ece":0.1944,"buckets":[{"lo":0,"hi":0.4,"n":11,"share":0.055,"meanTop":0.3808,"best":0.1818,"bestCI":0.2279,"lossPot":0.13446,"lossPotCI":0.09308},{"lo":0.4,"hi":0.6,"n":166,"share":0.83,"meanTop":0.4942,"best":0.2952,"bestCI":0.0694,"lossPot":0.07767,"lossPotCI":0.01923},{"lo":0.6,"hi":0.8,"n":22,"share":0.11,"meanTop":0.6658,"best":0.5909,"bestCI":0.2055,"lossPot":0.02151,"lossPotCI":0.0194},{"lo":0.8,"hi":1,"n":1,"share":0.005,"meanTop":0.867,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0}],"curve":[{"lo":0,"hi":0.4,"n":11,"share":0.055,"meanTop":0.3808,"best":0.1818,"bestCI":0.2279,"lossPot":0.13446,"lossPotCI":0.09308},{"lo":0.4,"hi":0.5,"n":91,"share":0.455,"meanTop":0.4495,"best":0.2308,"bestCI":0.0866,"lossPot":0.0779,"lossPotCI":0.02114},{"lo":0.5,"hi":0.6,"n":75,"share":0.375,"meanTop":0.5484,"best":0.3733,"bestCI":0.1095,"lossPot":0.0774,"lossPotCI":0.03414},{"lo":0.6,"hi":0.7,"n":15,"share":0.075,"meanTop":0.6389,"best":0.4667,"bestCI":0.2525,"lossPot":0.02583,"lossPotCI":0.0264},{"lo":0.7,"hi":0.8,"n":7,"share":0.035,"meanTop":0.7235,"best":0.8571,"bestCI":0.2592,"lossPot":0.01224,"lossPotCI":0.02399},{"lo":0.8,"hi":0.9,"n":1,"share":0.005,"meanTop":0.867,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"upstage/solar-decide","name":"Upstage Solar Decide","short":"Solar","n":200,"meanTop":0.5991,"best":0.475,"lossPot":0.05927,"ece":0.1329,"buckets":[{"lo":0,"hi":0.4,"n":3,"share":0.015,"meanTop":0.3755,"best":0.6667,"bestCI":0.5334,"lossPot":0.00468,"lossPotCI":0.00918},{"lo":0.4,"hi":0.6,"n":113,"share":0.565,"meanTop":0.5041,"best":0.469,"bestCI":0.092,"lossPot":0.06993,"lossPotCI":0.02574},{"lo":0.6,"hi":0.8,"n":58,"share":0.29,"meanTop":0.6624,"best":0.3966,"bestCI":0.1259,"lossPot":0.05734,"lossPotCI":0.02896},{"lo":0.8,"hi":1,"n":26,"share":0.13,"meanTop":0.897,"best":0.6538,"bestCI":0.1829,"lossPot":0.02357,"lossPotCI":0.02388}],"curve":[{"lo":0,"hi":0.4,"n":3,"share":0.015,"meanTop":0.3755,"best":0.6667,"bestCI":0.5334,"lossPot":0.00468,"lossPotCI":0.00918},{"lo":0.4,"hi":0.5,"n":51,"share":0.255,"meanTop":0.459,"best":0.451,"bestCI":0.1366,"lossPot":0.06382,"lossPotCI":0.03779},{"lo":0.5,"hi":0.6,"n":62,"share":0.31,"meanTop":0.5412,"best":0.4839,"bestCI":0.1244,"lossPot":0.07496,"lossPotCI":0.03537},{"lo":0.6,"hi":0.7,"n":45,"share":0.225,"meanTop":0.6358,"best":0.4,"bestCI":0.1431,"lossPot":0.05409,"lossPotCI":0.0287},{"lo":0.7,"hi":0.8,"n":13,"share":0.065,"meanTop":0.7544,"best":0.3846,"bestCI":0.2645,"lossPot":0.06856,"lossPotCI":0.08529},{"lo":0.8,"hi":0.9,"n":14,"share":0.07,"meanTop":0.8465,"best":0.6429,"bestCI":0.251,"lossPot":0.03614,"lossPotCI":0.04304},{"lo":0.9,"hi":1,"n":12,"share":0.06,"meanTop":0.956,"best":0.6667,"bestCI":0.2667,"lossPot":0.0089,"lossPotCI":0.0107}]},{"model":"upstage/solar-decide-flash","name":"Upstage Solar Decide Flash","short":"Solar Flash","n":200,"meanTop":0.5128,"best":0.42,"lossPot":0.07729,"ece":0.0928,"buckets":[{"lo":0,"hi":0.4,"n":1,"share":0.005,"meanTop":0.3837,"best":0,"bestCI":0,"lossPot":0.11778,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":175,"share":0.875,"meanTop":0.4961,"best":0.4286,"bestCI":0.0733,"lossPot":0.07472,"lossPotCI":0.0225},{"lo":0.6,"hi":0.8,"n":24,"share":0.12,"meanTop":0.6397,"best":0.375,"bestCI":0.1937,"lossPot":0.09437,"lossPotCI":0.08617},{"lo":0.8,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}],"curve":[{"lo":0,"hi":0.4,"n":1,"share":0.005,"meanTop":0.3837,"best":0,"bestCI":0,"lossPot":0.11778,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":101,"share":0.505,"meanTop":0.4586,"best":0.3465,"bestCI":0.0928,"lossPot":0.07323,"lossPotCI":0.02736},{"lo":0.5,"hi":0.6,"n":74,"share":0.37,"meanTop":0.5474,"best":0.5405,"bestCI":0.1135,"lossPot":0.07676,"lossPotCI":0.03811},{"lo":0.6,"hi":0.7,"n":22,"share":0.11,"meanTop":0.6316,"best":0.4091,"bestCI":0.2055,"lossPot":0.08894,"lossPotCI":0.09231},{"lo":0.7,"hi":0.8,"n":2,"share":0.01,"meanTop":0.7288,"best":0,"bestCI":0,"lossPot":0.15413,"lossPotCI":0.2575},{"lo":0.8,"hi":0.9,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]}],"variants":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"coach","n":682,"meanTop":0.6791,"best":0.6305,"lossPot":0.08621,"ece":0.096,"buckets":[{"lo":0,"hi":0.4,"n":21,"share":0.0308,"meanTop":0.371,"best":0.381,"bestCI":0.2077,"lossPot":0.38436,"lossPotCI":0.14742},{"lo":0.4,"hi":0.6,"n":219,"share":0.3211,"meanTop":0.5111,"best":0.3242,"bestCI":0.062,"lossPot":0.16698,"lossPotCI":0.03015},{"lo":0.6,"hi":0.8,"n":241,"share":0.3534,"meanTop":0.6808,"best":0.7469,"bestCI":0.0549,"lossPot":0.04466,"lossPotCI":0.01722},{"lo":0.8,"hi":1,"n":201,"share":0.2947,"meanTop":0.8925,"best":0.8507,"bestCI":0.0493,"lossPot":0.01687,"lossPotCI":0.00994}],"curve":[{"lo":0,"hi":0.4,"n":21,"share":0.0308,"meanTop":0.371,"best":0.381,"bestCI":0.2077,"lossPot":0.38436,"lossPotCI":0.14742},{"lo":0.4,"hi":0.5,"n":76,"share":0.1114,"meanTop":0.4439,"best":0.1711,"bestCI":0.0847,"lossPot":0.29231,"lossPotCI":0.05753},{"lo":0.5,"hi":0.6,"n":143,"share":0.2097,"meanTop":0.5467,"best":0.4056,"bestCI":0.0805,"lossPot":0.10038,"lossPotCI":0.02937},{"lo":0.6,"hi":0.7,"n":144,"share":0.2111,"meanTop":0.6396,"best":0.7153,"bestCI":0.0737,"lossPot":0.04004,"lossPotCI":0.02124},{"lo":0.7,"hi":0.8,"n":97,"share":0.1422,"meanTop":0.742,"best":0.7938,"bestCI":0.0805,"lossPot":0.05152,"lossPotCI":0.029},{"lo":0.8,"hi":0.9,"n":102,"share":0.1496,"meanTop":0.8479,"best":0.8333,"bestCI":0.0723,"lossPot":0.0199,"lossPotCI":0.01485},{"lo":0.9,"hi":1,"n":99,"share":0.1452,"meanTop":0.9385,"best":0.8687,"bestCI":0.0665,"lossPot":0.01375,"lossPotCI":0.0132}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"eq","n":682,"meanTop":0.8293,"best":0.6202,"lossPot":0.07214,"ece":0.2149,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":59,"share":0.0865,"meanTop":0.5425,"best":0.5763,"bestCI":0.1261,"lossPot":0.08966,"lossPotCI":0.04417},{"lo":0.6,"hi":0.8,"n":190,"share":0.2786,"meanTop":0.6988,"best":0.5474,"bestCI":0.0708,"lossPot":0.08866,"lossPotCI":0.02526},{"lo":0.8,"hi":1,"n":433,"share":0.6349,"meanTop":0.9256,"best":0.6582,"bestCI":0.0447,"lossPot":0.06251,"lossPotCI":0.01326}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.5,"hi":0.6,"n":59,"share":0.0865,"meanTop":0.5425,"best":0.5763,"bestCI":0.1261,"lossPot":0.08966,"lossPotCI":0.04417},{"lo":0.6,"hi":0.7,"n":92,"share":0.1349,"meanTop":0.6482,"best":0.4674,"bestCI":0.102,"lossPot":0.07895,"lossPotCI":0.02741},{"lo":0.7,"hi":0.8,"n":98,"share":0.1437,"meanTop":0.7464,"best":0.6224,"bestCI":0.096,"lossPot":0.09777,"lossPotCI":0.04173},{"lo":0.8,"hi":0.9,"n":133,"share":0.195,"meanTop":0.8457,"best":0.6617,"bestCI":0.0804,"lossPot":0.06467,"lossPotCI":0.02375},{"lo":0.9,"hi":1,"n":300,"share":0.4399,"meanTop":0.961,"best":0.6567,"bestCI":0.0537,"lossPot":0.06156,"lossPotCI":0.016}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"eqrange","n":661,"meanTop":0.8485,"best":0.8003,"lossPot":0.01878,"ece":0.1008,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":68,"share":0.1029,"meanTop":0.5384,"best":0.7059,"bestCI":0.1083,"lossPot":0.03651,"lossPotCI":0.02249},{"lo":0.6,"hi":0.8,"n":135,"share":0.2042,"meanTop":0.7036,"best":0.7481,"bestCI":0.0732,"lossPot":0.03181,"lossPotCI":0.02366},{"lo":0.8,"hi":1,"n":458,"share":0.6929,"meanTop":0.9372,"best":0.8297,"bestCI":0.0344,"lossPot":0.0123,"lossPotCI":0.00551}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":1,"share":0.0015,"meanTop":0.49,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.5,"hi":0.6,"n":67,"share":0.1014,"meanTop":0.5391,"best":0.7015,"bestCI":0.1096,"lossPot":0.03705,"lossPotCI":0.0228},{"lo":0.6,"hi":0.7,"n":60,"share":0.0908,"meanTop":0.6463,"best":0.7333,"bestCI":0.1119,"lossPot":0.02263,"lossPotCI":0.01606},{"lo":0.7,"hi":0.8,"n":75,"share":0.1135,"meanTop":0.7493,"best":0.76,"bestCI":0.0967,"lossPot":0.03915,"lossPotCI":0.04067},{"lo":0.8,"hi":0.9,"n":132,"share":0.1997,"meanTop":0.8504,"best":0.8106,"bestCI":0.0668,"lossPot":0.02429,"lossPotCI":0.01516},{"lo":0.9,"hi":1,"n":326,"share":0.4932,"meanTop":0.9724,"best":0.8374,"bestCI":0.0401,"lossPot":0.00745,"lossPotCI":0.00463}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"minimal","n":337,"meanTop":0.807,"best":0.7567,"lossPot":0.04131,"ece":0.1341,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":44,"share":0.1306,"meanTop":0.5477,"best":0.7273,"bestCI":0.1316,"lossPot":0.05379,"lossPotCI":0.03741},{"lo":0.6,"hi":0.8,"n":107,"share":0.3175,"meanTop":0.7083,"best":0.7664,"bestCI":0.0802,"lossPot":0.04906,"lossPotCI":0.02619},{"lo":0.8,"hi":1,"n":186,"share":0.5519,"meanTop":0.9251,"best":0.7581,"bestCI":0.0615,"lossPot":0.0339,"lossPotCI":0.0144}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.5,"hi":0.6,"n":44,"share":0.1306,"meanTop":0.5477,"best":0.7273,"bestCI":0.1316,"lossPot":0.05379,"lossPotCI":0.03741},{"lo":0.6,"hi":0.7,"n":44,"share":0.1306,"meanTop":0.6468,"best":0.7273,"bestCI":0.1316,"lossPot":0.05671,"lossPotCI":0.04914},{"lo":0.7,"hi":0.8,"n":63,"share":0.1869,"meanTop":0.7513,"best":0.7937,"bestCI":0.0999,"lossPot":0.04371,"lossPotCI":0.0286},{"lo":0.8,"hi":0.9,"n":52,"share":0.1543,"meanTop":0.8388,"best":0.6538,"bestCI":0.1293,"lossPot":0.06335,"lossPotCI":0.04086},{"lo":0.9,"hi":1,"n":134,"share":0.3976,"meanTop":0.9586,"best":0.7985,"bestCI":0.0679,"lossPot":0.02248,"lossPotCI":0.01177}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"multi","n":661,"meanTop":0.7751,"best":0.8018,"lossPot":0.02472,"ece":0.0726,"buckets":[{"lo":0,"hi":0.4,"n":1,"share":0.0015,"meanTop":0.3867,"best":0,"bestCI":0,"lossPot":0.28741,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":91,"share":0.1377,"meanTop":0.5415,"best":0.6923,"bestCI":0.0948,"lossPot":0.05482,"lossPotCI":0.0365},{"lo":0.6,"hi":0.8,"n":249,"share":0.3767,"meanTop":0.708,"best":0.7831,"bestCI":0.0512,"lossPot":0.02001,"lossPotCI":0.00881},{"lo":0.8,"hi":1,"n":320,"share":0.4841,"meanTop":0.895,"best":0.85,"bestCI":0.0391,"lossPot":0.019,"lossPotCI":0.00795}],"curve":[{"lo":0,"hi":0.4,"n":1,"share":0.0015,"meanTop":0.3867,"best":0,"bestCI":0,"lossPot":0.28741,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":5,"share":0.0076,"meanTop":0.4773,"best":0.4,"bestCI":0.4294,"lossPot":0.38105,"lossPotCI":0.54066},{"lo":0.5,"hi":0.6,"n":86,"share":0.1301,"meanTop":0.5452,"best":0.7093,"bestCI":0.096,"lossPot":0.03585,"lossPotCI":0.01991},{"lo":0.6,"hi":0.7,"n":111,"share":0.1679,"meanTop":0.6497,"best":0.7838,"bestCI":0.0766,"lossPot":0.02367,"lossPotCI":0.01445},{"lo":0.7,"hi":0.8,"n":138,"share":0.2088,"meanTop":0.7548,"best":0.7826,"bestCI":0.0688,"lossPot":0.01707,"lossPotCI":0.01088},{"lo":0.8,"hi":0.9,"n":169,"share":0.2557,"meanTop":0.8493,"best":0.8166,"bestCI":0.0584,"lossPot":0.01838,"lossPotCI":0.0089},{"lo":0.9,"hi":1,"n":151,"share":0.2284,"meanTop":0.9462,"best":0.8874,"bestCI":0.0504,"lossPot":0.0197,"lossPotCI":0.01363}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"noul","n":335,"meanTop":0.7886,"best":0.7881,"lossPot":0.03114,"ece":0.0767,"buckets":[{"lo":0,"hi":0.4,"n":1,"share":0.003,"meanTop":0.3571,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":26,"share":0.0776,"meanTop":0.5366,"best":0.7692,"bestCI":0.162,"lossPot":0.0256,"lossPotCI":0.02569},{"lo":0.6,"hi":0.8,"n":129,"share":0.3851,"meanTop":0.714,"best":0.7442,"bestCI":0.0753,"lossPot":0.04935,"lossPotCI":0.02068},{"lo":0.8,"hi":1,"n":179,"share":0.5343,"meanTop":0.8815,"best":0.8212,"bestCI":0.0561,"lossPot":0.01899,"lossPotCI":0.00978}],"curve":[{"lo":0,"hi":0.4,"n":1,"share":0.003,"meanTop":0.3571,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":2,"share":0.006,"meanTop":0.4518,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.5,"hi":0.6,"n":24,"share":0.0716,"meanTop":0.5437,"best":0.75,"bestCI":0.1732,"lossPot":0.02773,"lossPotCI":0.0277},{"lo":0.6,"hi":0.7,"n":51,"share":0.1522,"meanTop":0.6502,"best":0.7059,"bestCI":0.1251,"lossPot":0.04531,"lossPotCI":0.03316},{"lo":0.7,"hi":0.8,"n":78,"share":0.2328,"meanTop":0.7557,"best":0.7692,"bestCI":0.0935,"lossPot":0.052,"lossPotCI":0.0266},{"lo":0.8,"hi":0.9,"n":111,"share":0.3313,"meanTop":0.8455,"best":0.8649,"bestCI":0.0636,"lossPot":0.01709,"lossPotCI":0.01184},{"lo":0.9,"hi":1,"n":68,"share":0.203,"meanTop":0.9402,"best":0.75,"bestCI":0.1029,"lossPot":0.0221,"lossPotCI":0.01709}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"nuts","n":2213,"meanTop":0.8512,"best":0.7375,"lossPot":0.03554,"ece":0.137,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":169,"share":0.0764,"meanTop":0.5481,"best":0.6805,"bestCI":0.0703,"lossPot":0.03361,"lossPotCI":0.01585},{"lo":0.6,"hi":0.8,"n":562,"share":0.254,"meanTop":0.702,"best":0.6637,"bestCI":0.0391,"lossPot":0.05164,"lossPotCI":0.01015},{"lo":0.8,"hi":1,"n":1482,"share":0.6697,"meanTop":0.9423,"best":0.7719,"bestCI":0.0214,"lossPot":0.02966,"lossPotCI":0.00528}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":4,"share":0.0018,"meanTop":0.4875,"best":0.75,"bestCI":0.4244,"lossPot":0.06746,"lossPotCI":0.13222},{"lo":0.5,"hi":0.6,"n":165,"share":0.0746,"meanTop":0.5496,"best":0.6788,"bestCI":0.0712,"lossPot":0.03279,"lossPotCI":0.01597},{"lo":0.6,"hi":0.7,"n":251,"share":0.1134,"meanTop":0.6481,"best":0.6614,"bestCI":0.0585,"lossPot":0.04362,"lossPotCI":0.01397},{"lo":0.7,"hi":0.8,"n":311,"share":0.1405,"meanTop":0.7455,"best":0.6656,"bestCI":0.0524,"lossPot":0.05812,"lossPotCI":0.01444},{"lo":0.8,"hi":0.9,"n":362,"share":0.1636,"meanTop":0.8501,"best":0.7044,"bestCI":0.047,"lossPot":0.0447,"lossPotCI":0.01302},{"lo":0.9,"hi":1,"n":1120,"share":0.5061,"meanTop":0.9722,"best":0.7937,"bestCI":0.0237,"lossPot":0.02479,"lossPotCI":0.00555}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"shortstack","n":613,"meanTop":0.8883,"best":0.7162,"lossPot":0.04304,"ece":0.1722,"buckets":[{"lo":0,"hi":0.4,"n":4,"share":0.0065,"meanTop":0.3775,"best":0,"bestCI":0,"lossPot":0.33755,"lossPotCI":0.25614},{"lo":0.4,"hi":0.6,"n":36,"share":0.0587,"meanTop":0.5133,"best":0.2222,"bestCI":0.1358,"lossPot":0.21499,"lossPotCI":0.07517},{"lo":0.6,"hi":0.8,"n":86,"share":0.1403,"meanTop":0.7052,"best":0.4884,"bestCI":0.1056,"lossPot":0.04618,"lossPotCI":0.01545},{"lo":0.8,"hi":1,"n":487,"share":0.7945,"meanTop":0.9526,"best":0.7988,"bestCI":0.0356,"lossPot":0.02736,"lossPotCI":0.00865}],"curve":[{"lo":0,"hi":0.4,"n":4,"share":0.0065,"meanTop":0.3775,"best":0,"bestCI":0,"lossPot":0.33755,"lossPotCI":0.25614},{"lo":0.4,"hi":0.5,"n":14,"share":0.0228,"meanTop":0.46,"best":0.2857,"bestCI":0.2366,"lossPot":0.2022,"lossPotCI":0.10674},{"lo":0.5,"hi":0.6,"n":22,"share":0.0359,"meanTop":0.5473,"best":0.1818,"bestCI":0.1612,"lossPot":0.22314,"lossPotCI":0.10437},{"lo":0.6,"hi":0.7,"n":34,"share":0.0555,"meanTop":0.6379,"best":0.5,"bestCI":0.1681,"lossPot":0.04923,"lossPotCI":0.02392},{"lo":0.7,"hi":0.8,"n":52,"share":0.0848,"meanTop":0.7492,"best":0.4808,"bestCI":0.1358,"lossPot":0.04419,"lossPotCI":0.02037},{"lo":0.8,"hi":0.9,"n":78,"share":0.1272,"meanTop":0.8518,"best":0.6282,"bestCI":0.1073,"lossPot":0.0109,"lossPotCI":0.00608},{"lo":0.9,"hi":1,"n":409,"share":0.6672,"meanTop":0.9718,"best":0.8313,"bestCI":0.0363,"lossPot":0.03049,"lossPotCI":0.01021}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"sizing","n":661,"meanTop":0.8477,"best":0.7882,"lossPot":0.02015,"ece":0.1129,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":64,"share":0.0968,"meanTop":0.5477,"best":0.6562,"bestCI":0.1164,"lossPot":0.06517,"lossPotCI":0.05104},{"lo":0.6,"hi":0.8,"n":157,"share":0.2375,"meanTop":0.6992,"best":0.7643,"bestCI":0.0664,"lossPot":0.02314,"lossPotCI":0.01355},{"lo":0.8,"hi":1,"n":440,"share":0.6657,"meanTop":0.9443,"best":0.8159,"bestCI":0.0362,"lossPot":0.01254,"lossPotCI":0.00486}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":1,"share":0.0015,"meanTop":0.47,"best":0,"bestCI":0,"lossPot":1.45951,"lossPotCI":0},{"lo":0.5,"hi":0.6,"n":63,"share":0.0953,"meanTop":0.5489,"best":0.6667,"bestCI":0.1164,"lossPot":0.04304,"lossPotCI":0.02733},{"lo":0.6,"hi":0.7,"n":71,"share":0.1074,"meanTop":0.6425,"best":0.7324,"bestCI":0.103,"lossPot":0.03222,"lossPotCI":0.02595},{"lo":0.7,"hi":0.8,"n":86,"share":0.1301,"meanTop":0.7459,"best":0.7907,"bestCI":0.086,"lossPot":0.01564,"lossPotCI":0.01231},{"lo":0.8,"hi":0.9,"n":93,"share":0.1407,"meanTop":0.8501,"best":0.7957,"bestCI":0.0819,"lossPot":0.0234,"lossPotCI":0.01462},{"lo":0.9,"hi":1,"n":347,"share":0.525,"meanTop":0.9695,"best":0.8213,"bestCI":0.0403,"lossPot":0.00963,"lossPotCI":0.00473}]},{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","variant":"v2","n":2681,"meanTop":0.789,"best":0.7079,"lossPot":0.0442,"ece":0.0836,"buckets":[{"lo":0,"hi":0.4,"n":1,"share":0.0004,"meanTop":0.39,"best":0,"bestCI":0,"lossPot":1.45951,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":367,"share":0.1369,"meanTop":0.5423,"best":0.4932,"bestCI":0.0512,"lossPot":0.07758,"lossPotCI":0.01423},{"lo":0.6,"hi":0.8,"n":898,"share":0.3349,"meanTop":0.7012,"best":0.6837,"bestCI":0.0304,"lossPot":0.04829,"lossPotCI":0.00792},{"lo":0.8,"hi":1,"n":1415,"share":0.5278,"meanTop":0.9089,"best":0.7795,"bestCI":0.0216,"lossPot":0.03194,"lossPotCI":0.00575}],"curve":[{"lo":0,"hi":0.4,"n":1,"share":0.0004,"meanTop":0.39,"best":0,"bestCI":0,"lossPot":1.45951,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":31,"share":0.0116,"meanTop":0.47,"best":0.4194,"bestCI":0.1737,"lossPot":0.10444,"lossPotCI":0.05006},{"lo":0.5,"hi":0.6,"n":336,"share":0.1253,"meanTop":0.549,"best":0.5,"bestCI":0.0535,"lossPot":0.07511,"lossPotCI":0.01484},{"lo":0.6,"hi":0.7,"n":403,"share":0.1503,"meanTop":0.6467,"best":0.6551,"bestCI":0.0464,"lossPot":0.05515,"lossPotCI":0.01251},{"lo":0.7,"hi":0.8,"n":495,"share":0.1846,"meanTop":0.7456,"best":0.7071,"bestCI":0.0401,"lossPot":0.0427,"lossPotCI":0.01011},{"lo":0.8,"hi":0.9,"n":582,"share":0.2171,"meanTop":0.8468,"best":0.7509,"bestCI":0.0351,"lossPot":0.03514,"lossPotCI":0.00814},{"lo":0.9,"hi":1,"n":833,"share":0.3107,"meanTop":0.9524,"best":0.7995,"bestCI":0.0272,"lossPot":0.02971,"lossPotCI":0.00794}]},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","variant":"nuts","n":1868,"meanTop":0.8349,"best":0.7404,"lossPot":0.02163,"ece":0.1376,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":156,"share":0.0835,"meanTop":0.5403,"best":0.7051,"bestCI":0.0716,"lossPot":0.04733,"lossPotCI":0.02159},{"lo":0.6,"hi":0.8,"n":496,"share":0.2655,"meanTop":0.7205,"best":0.7097,"bestCI":0.0399,"lossPot":0.01982,"lossPotCI":0.0053},{"lo":0.8,"hi":1,"n":1216,"share":0.651,"meanTop":0.9193,"best":0.7574,"bestCI":0.0241,"lossPot":0.01908,"lossPotCI":0.00367}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":22,"share":0.0118,"meanTop":0.4767,"best":0.4091,"bestCI":0.2055,"lossPot":0.11032,"lossPotCI":0.07311},{"lo":0.5,"hi":0.6,"n":134,"share":0.0717,"meanTop":0.5507,"best":0.7537,"bestCI":0.0729,"lossPot":0.03698,"lossPotCI":0.02172},{"lo":0.6,"hi":0.7,"n":169,"share":0.0905,"meanTop":0.6506,"best":0.7278,"bestCI":0.0671,"lossPot":0.01897,"lossPotCI":0.00818},{"lo":0.7,"hi":0.8,"n":327,"share":0.1751,"meanTop":0.7565,"best":0.7003,"bestCI":0.0497,"lossPot":0.02026,"lossPotCI":0.00685},{"lo":0.8,"hi":0.9,"n":474,"share":0.2537,"meanTop":0.8498,"best":0.6941,"bestCI":0.0415,"lossPot":0.02361,"lossPotCI":0.00625},{"lo":0.9,"hi":1,"n":742,"share":0.3972,"meanTop":0.9637,"best":0.7978,"bestCI":0.0289,"lossPot":0.01618,"lossPotCI":0.00448}]},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","variant":"sizing","n":1568,"meanTop":0.8444,"best":0.7207,"lossPot":0.02482,"ece":0.1411,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":143,"share":0.0912,"meanTop":0.5438,"best":0.6154,"bestCI":0.0797,"lossPot":0.04596,"lossPotCI":0.01705},{"lo":0.6,"hi":0.8,"n":352,"share":0.2245,"meanTop":0.7196,"best":0.6875,"bestCI":0.0484,"lossPot":0.03362,"lossPotCI":0.01005},{"lo":0.8,"hi":1,"n":1073,"share":0.6843,"meanTop":0.9254,"best":0.7456,"bestCI":0.0261,"lossPot":0.01911,"lossPotCI":0.00383}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":20,"share":0.0128,"meanTop":0.4746,"best":0.5,"bestCI":0.2191,"lossPot":0.02887,"lossPotCI":0.02297},{"lo":0.5,"hi":0.6,"n":123,"share":0.0784,"meanTop":0.555,"best":0.6341,"bestCI":0.0851,"lossPot":0.04874,"lossPotCI":0.01945},{"lo":0.6,"hi":0.7,"n":120,"share":0.0765,"meanTop":0.6551,"best":0.6833,"bestCI":0.0832,"lossPot":0.04371,"lossPotCI":0.0219},{"lo":0.7,"hi":0.8,"n":232,"share":0.148,"meanTop":0.7529,"best":0.6897,"bestCI":0.0595,"lossPot":0.0284,"lossPotCI":0.01018},{"lo":0.8,"hi":0.9,"n":349,"share":0.2226,"meanTop":0.8522,"best":0.6705,"bestCI":0.0493,"lossPot":0.02396,"lossPotCI":0.00713},{"lo":0.9,"hi":1,"n":724,"share":0.4617,"meanTop":0.9606,"best":0.7818,"bestCI":0.0301,"lossPot":0.01677,"lossPotCI":0.00451}]},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","variant":"v2","n":2268,"meanTop":0.7359,"best":0.6468,"lossPot":0.03692,"ece":0.1091,"buckets":[{"lo":0,"hi":0.4,"n":8,"share":0.0035,"meanTop":0.3745,"best":0.375,"bestCI":0.3355,"lossPot":0.06874,"lossPotCI":0.05113},{"lo":0.4,"hi":0.6,"n":432,"share":0.1905,"meanTop":0.5333,"best":0.5856,"bestCI":0.0465,"lossPot":0.05006,"lossPotCI":0.01094},{"lo":0.6,"hi":0.8,"n":993,"share":0.4378,"meanTop":0.7127,"best":0.6324,"bestCI":0.03,"lossPot":0.0353,"lossPotCI":0.00491},{"lo":0.8,"hi":1,"n":835,"share":0.3682,"meanTop":0.872,"best":0.6982,"bestCI":0.0311,"lossPot":0.03175,"lossPotCI":0.00654}],"curve":[{"lo":0,"hi":0.4,"n":8,"share":0.0035,"meanTop":0.3745,"best":0.375,"bestCI":0.3355,"lossPot":0.06874,"lossPotCI":0.05113},{"lo":0.4,"hi":0.5,"n":100,"share":0.0441,"meanTop":0.4696,"best":0.56,"bestCI":0.0973,"lossPot":0.04653,"lossPotCI":0.01953},{"lo":0.5,"hi":0.6,"n":332,"share":0.1464,"meanTop":0.5524,"best":0.5934,"bestCI":0.0528,"lossPot":0.05113,"lossPotCI":0.01297},{"lo":0.6,"hi":0.7,"n":401,"share":0.1768,"meanTop":0.6521,"best":0.596,"bestCI":0.048,"lossPot":0.03911,"lossPotCI":0.00817},{"lo":0.7,"hi":0.8,"n":592,"share":0.261,"meanTop":0.7537,"best":0.6571,"bestCI":0.0382,"lossPot":0.03272,"lossPotCI":0.00609},{"lo":0.8,"hi":0.9,"n":599,"share":0.2641,"meanTop":0.8465,"best":0.6895,"bestCI":0.0371,"lossPot":0.02661,"lossPotCI":0.00614},{"lo":0.9,"hi":1,"n":236,"share":0.1041,"meanTop":0.9365,"best":0.7203,"bestCI":0.0573,"lossPot":0.0448,"lossPotCI":0.01703}]},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef","variant":"nuts","n":624,"meanTop":0.6038,"best":0.7724,"lossPot":0.01764,"ece":0.1732,"buckets":[{"lo":0,"hi":0.4,"n":23,"share":0.0369,"meanTop":0.3785,"best":0.5217,"bestCI":0.2042,"lossPot":0.04433,"lossPotCI":0.03415},{"lo":0.4,"hi":0.6,"n":322,"share":0.516,"meanTop":0.5135,"best":0.7484,"bestCI":0.0474,"lossPot":0.01964,"lossPotCI":0.00712},{"lo":0.6,"hi":0.8,"n":216,"share":0.3462,"meanTop":0.6819,"best":0.8102,"bestCI":0.0523,"lossPot":0.01631,"lossPotCI":0.00855},{"lo":0.8,"hi":1,"n":63,"share":0.101,"meanTop":0.8794,"best":0.8571,"bestCI":0.0864,"lossPot":0.00219,"lossPotCI":0.00177}],"curve":[{"lo":0,"hi":0.4,"n":23,"share":0.0369,"meanTop":0.3785,"best":0.5217,"bestCI":0.2042,"lossPot":0.04433,"lossPotCI":0.03415},{"lo":0.4,"hi":0.5,"n":120,"share":0.1923,"meanTop":0.4544,"best":0.7167,"bestCI":0.0806,"lossPot":0.02442,"lossPotCI":0.01197},{"lo":0.5,"hi":0.6,"n":202,"share":0.3237,"meanTop":0.5486,"best":0.7673,"bestCI":0.0583,"lossPot":0.0168,"lossPotCI":0.00883},{"lo":0.6,"hi":0.7,"n":136,"share":0.2179,"meanTop":0.6468,"best":0.8235,"bestCI":0.0641,"lossPot":0.0122,"lossPotCI":0.0074},{"lo":0.7,"hi":0.8,"n":80,"share":0.1282,"meanTop":0.7417,"best":0.7875,"bestCI":0.0896,"lossPot":0.02329,"lossPotCI":0.01935},{"lo":0.8,"hi":0.9,"n":39,"share":0.0625,"meanTop":0.8466,"best":0.8462,"bestCI":0.1132,"lossPot":0.0027,"lossPotCI":0.00264},{"lo":0.9,"hi":1,"n":24,"share":0.0385,"meanTop":0.9327,"best":0.875,"bestCI":0.1323,"lossPot":0.00137,"lossPotCI":0.00184}]},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef","variant":"v2","n":824,"meanTop":0.5127,"best":0.6917,"lossPot":0.03281,"ece":0.1797,"buckets":[{"lo":0,"hi":0.4,"n":123,"share":0.1493,"meanTop":0.3674,"best":0.4553,"bestCI":0.088,"lossPot":0.06417,"lossPotCI":0.01934},{"lo":0.4,"hi":0.6,"n":557,"share":0.676,"meanTop":0.5036,"best":0.7092,"bestCI":0.0377,"lossPot":0.02894,"lossPotCI":0.00653},{"lo":0.6,"hi":0.8,"n":133,"share":0.1614,"meanTop":0.6579,"best":0.8271,"bestCI":0.0643,"lossPot":0.02265,"lossPotCI":0.01429},{"lo":0.8,"hi":1,"n":11,"share":0.0133,"meanTop":0.8419,"best":0.8182,"bestCI":0.2279,"lossPot":0.00108,"lossPotCI":0.00168}],"curve":[{"lo":0,"hi":0.4,"n":123,"share":0.1493,"meanTop":0.3674,"best":0.4553,"bestCI":0.088,"lossPot":0.06417,"lossPotCI":0.01934},{"lo":0.4,"hi":0.5,"n":252,"share":0.3058,"meanTop":0.4514,"best":0.6587,"bestCI":0.0585,"lossPot":0.03624,"lossPotCI":0.01057},{"lo":0.5,"hi":0.6,"n":305,"share":0.3701,"meanTop":0.5468,"best":0.7508,"bestCI":0.0485,"lossPot":0.0229,"lossPotCI":0.00809},{"lo":0.6,"hi":0.7,"n":108,"share":0.1311,"meanTop":0.6385,"best":0.8333,"bestCI":0.0703,"lossPot":0.02317,"lossPotCI":0.01672},{"lo":0.7,"hi":0.8,"n":25,"share":0.0303,"meanTop":0.7417,"best":0.8,"bestCI":0.1568,"lossPot":0.02041,"lossPotCI":0.02435},{"lo":0.8,"hi":0.9,"n":11,"share":0.0133,"meanTop":0.8419,"best":0.8182,"bestCI":0.2279,"lossPot":0.00108,"lossPotCI":0.00168},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev","variant":"nuts","n":300,"meanTop":0.732,"best":0.6833,"lossPot":0.0242,"ece":0.1129,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":66,"share":0.22,"meanTop":0.5344,"best":0.6212,"bestCI":0.117,"lossPot":0.0349,"lossPotCI":0.01817},{"lo":0.6,"hi":0.8,"n":125,"share":0.4167,"meanTop":0.6874,"best":0.648,"bestCI":0.0837,"lossPot":0.03005,"lossPotCI":0.01262},{"lo":0.8,"hi":1,"n":109,"share":0.3633,"meanTop":0.9026,"best":0.7615,"bestCI":0.08,"lossPot":0.01101,"lossPotCI":0.00802}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":12,"share":0.04,"meanTop":0.4742,"best":0.4167,"bestCI":0.2789,"lossPot":0.05539,"lossPotCI":0.04544},{"lo":0.5,"hi":0.6,"n":54,"share":0.18,"meanTop":0.5478,"best":0.6667,"bestCI":0.1257,"lossPot":0.03034,"lossPotCI":0.01978},{"lo":0.6,"hi":0.7,"n":64,"share":0.2133,"meanTop":0.6372,"best":0.6875,"bestCI":0.1136,"lossPot":0.03414,"lossPotCI":0.01809},{"lo":0.7,"hi":0.8,"n":61,"share":0.2033,"meanTop":0.7402,"best":0.6066,"bestCI":0.1226,"lossPot":0.02576,"lossPotCI":0.01765},{"lo":0.8,"hi":0.9,"n":51,"share":0.17,"meanTop":0.8438,"best":0.6078,"bestCI":0.134,"lossPot":0.02134,"lossPotCI":0.01664},{"lo":0.9,"hi":1,"n":58,"share":0.1933,"meanTop":0.9543,"best":0.8966,"bestCI":0.0784,"lossPot":0.00192,"lossPotCI":0.00184}]},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev","variant":"v2","n":705,"meanTop":0.6184,"best":0.7035,"lossPot":0.02604,"ece":0.0941,"buckets":[{"lo":0,"hi":0.4,"n":9,"share":0.0128,"meanTop":0.3644,"best":0.4444,"bestCI":0.3246,"lossPot":0.02458,"lossPotCI":0.03024},{"lo":0.4,"hi":0.6,"n":307,"share":0.4355,"meanTop":0.5161,"best":0.6645,"bestCI":0.0528,"lossPot":0.03184,"lossPotCI":0.00973},{"lo":0.6,"hi":0.8,"n":340,"share":0.4823,"meanTop":0.6843,"best":0.7176,"bestCI":0.0478,"lossPot":0.02364,"lossPotCI":0.0078},{"lo":0.8,"hi":1,"n":49,"share":0.0695,"meanTop":0.848,"best":0.898,"bestCI":0.0848,"lossPot":0.00664,"lossPotCI":0.00825}],"curve":[{"lo":0,"hi":0.4,"n":9,"share":0.0128,"meanTop":0.3644,"best":0.4444,"bestCI":0.3246,"lossPot":0.02458,"lossPotCI":0.03024},{"lo":0.4,"hi":0.5,"n":105,"share":0.1489,"meanTop":0.4566,"best":0.5524,"bestCI":0.0951,"lossPot":0.05491,"lossPotCI":0.02354},{"lo":0.5,"hi":0.6,"n":202,"share":0.2865,"meanTop":0.5471,"best":0.7228,"bestCI":0.0617,"lossPot":0.01985,"lossPotCI":0.00788},{"lo":0.6,"hi":0.7,"n":194,"share":0.2752,"meanTop":0.6469,"best":0.7216,"bestCI":0.0631,"lossPot":0.02149,"lossPotCI":0.00857},{"lo":0.7,"hi":0.8,"n":146,"share":0.2071,"meanTop":0.734,"best":0.7123,"bestCI":0.0734,"lossPot":0.02651,"lossPotCI":0.01418},{"lo":0.8,"hi":0.9,"n":42,"share":0.0596,"meanTop":0.8345,"best":0.881,"bestCI":0.0979,"lossPot":0.00775,"lossPotCI":0.00959},{"lo":0.9,"hi":1,"n":7,"share":0.0099,"meanTop":0.9286,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"liquid/d1","name":"Liquid d1","short":"d1","variant":"nuts","n":300,"meanTop":0.8409,"best":0.7467,"lossPot":0.0179,"ece":0.1007,"buckets":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":28,"share":0.0933,"meanTop":0.5521,"best":0.5714,"bestCI":0.1833,"lossPot":0.03342,"lossPotCI":0.02525},{"lo":0.6,"hi":0.8,"n":70,"share":0.2333,"meanTop":0.7157,"best":0.7,"bestCI":0.1074,"lossPot":0.03618,"lossPotCI":0.02872},{"lo":0.8,"hi":1,"n":202,"share":0.6733,"meanTop":0.9244,"best":0.7871,"bestCI":0.0564,"lossPot":0.00942,"lossPotCI":0.00588}],"curve":[{"lo":0,"hi":0.4,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":7,"share":0.0233,"meanTop":0.4887,"best":0.4286,"bestCI":0.3666,"lossPot":0.00788,"lossPotCI":0.00706},{"lo":0.5,"hi":0.6,"n":21,"share":0.07,"meanTop":0.5733,"best":0.619,"bestCI":0.2077,"lossPot":0.04193,"lossPotCI":0.03297},{"lo":0.6,"hi":0.7,"n":27,"share":0.09,"meanTop":0.6554,"best":0.6296,"bestCI":0.1822,"lossPot":0.07395,"lossPotCI":0.07093},{"lo":0.7,"hi":0.8,"n":43,"share":0.1433,"meanTop":0.7535,"best":0.7442,"bestCI":0.1304,"lossPot":0.01246,"lossPotCI":0.01079},{"lo":0.8,"hi":0.9,"n":63,"share":0.21,"meanTop":0.8562,"best":0.7619,"bestCI":0.1052,"lossPot":0.01505,"lossPotCI":0.01601},{"lo":0.9,"hi":1,"n":139,"share":0.4633,"meanTop":0.9552,"best":0.7986,"bestCI":0.0667,"lossPot":0.00687,"lossPotCI":0.00452}]},{"model":"liquid/d1","name":"Liquid d1","short":"d1","variant":"v2","n":700,"meanTop":0.7779,"best":0.7157,"lossPot":0.02697,"ece":0.0789,"buckets":[{"lo":0,"hi":0.4,"n":2,"share":0.0029,"meanTop":0.3758,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":121,"share":0.1729,"meanTop":0.532,"best":0.5702,"bestCI":0.0882,"lossPot":0.0553,"lossPotCI":0.02644},{"lo":0.6,"hi":0.8,"n":217,"share":0.31,"meanTop":0.7071,"best":0.6452,"bestCI":0.0637,"lossPot":0.03515,"lossPotCI":0.01321},{"lo":0.8,"hi":1,"n":360,"share":0.5143,"meanTop":0.9054,"best":0.8056,"bestCI":0.0409,"lossPot":0.01267,"lossPotCI":0.00593}],"curve":[{"lo":0,"hi":0.4,"n":2,"share":0.0029,"meanTop":0.3758,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":27,"share":0.0386,"meanTop":0.4553,"best":0.5185,"bestCI":0.1885,"lossPot":0.04618,"lossPotCI":0.02477},{"lo":0.5,"hi":0.6,"n":94,"share":0.1343,"meanTop":0.5541,"best":0.5851,"bestCI":0.0996,"lossPot":0.05792,"lossPotCI":0.03332},{"lo":0.6,"hi":0.7,"n":94,"share":0.1343,"meanTop":0.6532,"best":0.6277,"bestCI":0.0977,"lossPot":0.03509,"lossPotCI":0.01789},{"lo":0.7,"hi":0.8,"n":123,"share":0.1757,"meanTop":0.7483,"best":0.6585,"bestCI":0.0838,"lossPot":0.0352,"lossPotCI":0.01893},{"lo":0.8,"hi":0.9,"n":162,"share":0.2314,"meanTop":0.8516,"best":0.7531,"bestCI":0.0664,"lossPot":0.01824,"lossPotCI":0.0119},{"lo":0.9,"hi":1,"n":198,"share":0.2829,"meanTop":0.9495,"best":0.8485,"bestCI":0.0499,"lossPot":0.00811,"lossPotCI":0.00458}]},{"model":"cloudflare/clef-flash","name":"Cloudflare Clef Flash","short":"Clef Flash","variant":"v2","n":200,"meanTop":0.4534,"best":0.32,"lossPot":0.07741,"ece":0.1593,"buckets":[{"lo":0,"hi":0.4,"n":44,"share":0.22,"meanTop":0.3798,"best":0.25,"bestCI":0.1279,"lossPot":0.07779,"lossPotCI":0.02637},{"lo":0.4,"hi":0.6,"n":146,"share":0.73,"meanTop":0.4602,"best":0.3151,"bestCI":0.0754,"lossPot":0.08013,"lossPotCI":0.01626},{"lo":0.6,"hi":0.8,"n":10,"share":0.05,"meanTop":0.6775,"best":0.7,"bestCI":0.284,"lossPot":0.03598,"lossPotCI":0.06603},{"lo":0.8,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}],"curve":[{"lo":0,"hi":0.4,"n":44,"share":0.22,"meanTop":0.3798,"best":0.25,"bestCI":0.1279,"lossPot":0.07779,"lossPotCI":0.02637},{"lo":0.4,"hi":0.5,"n":116,"share":0.58,"meanTop":0.4403,"best":0.2414,"bestCI":0.0779,"lossPot":0.08674,"lossPotCI":0.01775},{"lo":0.5,"hi":0.6,"n":30,"share":0.15,"meanTop":0.5369,"best":0.6,"bestCI":0.1753,"lossPot":0.05458,"lossPotCI":0.03871},{"lo":0.6,"hi":0.7,"n":7,"share":0.035,"meanTop":0.6391,"best":0.5714,"bestCI":0.3666,"lossPot":0.0514,"lossPotCI":0.09399},{"lo":0.7,"hi":0.8,"n":3,"share":0.015,"meanTop":0.7671,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.8,"hi":0.9,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"jaredpalmer/kev-4b","name":"Kev 4B","short":"Kev","variant":"v2","n":200,"meanTop":0.4499,"best":0.465,"lossPot":0.06263,"ece":0.0666,"buckets":[{"lo":0,"hi":0.4,"n":55,"share":0.275,"meanTop":0.3765,"best":0.3636,"bestCI":0.1271,"lossPot":0.08833,"lossPotCI":0.03257},{"lo":0.4,"hi":0.6,"n":135,"share":0.675,"meanTop":0.4668,"best":0.4815,"bestCI":0.0843,"lossPot":0.05641,"lossPotCI":0.01682},{"lo":0.6,"hi":0.8,"n":10,"share":0.05,"meanTop":0.6264,"best":0.8,"bestCI":0.2479,"lossPot":0.00535,"lossPotCI":0.0094},{"lo":0.8,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}],"curve":[{"lo":0,"hi":0.4,"n":55,"share":0.275,"meanTop":0.3765,"best":0.3636,"bestCI":0.1271,"lossPot":0.08833,"lossPotCI":0.03257},{"lo":0.4,"hi":0.5,"n":101,"share":0.505,"meanTop":0.44,"best":0.396,"bestCI":0.0954,"lossPot":0.06442,"lossPotCI":0.02032},{"lo":0.5,"hi":0.6,"n":34,"share":0.17,"meanTop":0.5462,"best":0.7353,"bestCI":0.1483,"lossPot":0.03261,"lossPotCI":0.02752},{"lo":0.6,"hi":0.7,"n":10,"share":0.05,"meanTop":0.6264,"best":0.8,"bestCI":0.2479,"lossPot":0.00535,"lossPotCI":0.0094},{"lo":0.7,"hi":0.8,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.8,"hi":0.9,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"perplexity/pplx-decider-v1.1-27b","name":"Perplexity Decider v1.1 27B","short":"Perplexity","variant":"v2","n":200,"meanTop":0.6512,"best":0.58,"lossPot":0.03521,"ece":0.1038,"buckets":[{"lo":0,"hi":0.4,"n":9,"share":0.045,"meanTop":0.3805,"best":0.5556,"bestCI":0.3246,"lossPot":0.04316,"lossPotCI":0.05142},{"lo":0.4,"hi":0.6,"n":67,"share":0.335,"meanTop":0.5204,"best":0.4328,"bestCI":0.1186,"lossPot":0.0542,"lossPotCI":0.01996},{"lo":0.6,"hi":0.8,"n":88,"share":0.44,"meanTop":0.689,"best":0.5568,"bestCI":0.1038,"lossPot":0.03339,"lossPotCI":0.01272},{"lo":0.8,"hi":1,"n":36,"share":0.18,"meanTop":0.8697,"best":0.9167,"bestCI":0.0903,"lossPot":0.00231,"lossPotCI":0.00319}],"curve":[{"lo":0,"hi":0.4,"n":9,"share":0.045,"meanTop":0.3805,"best":0.5556,"bestCI":0.3246,"lossPot":0.04316,"lossPotCI":0.05142},{"lo":0.4,"hi":0.5,"n":25,"share":0.125,"meanTop":0.4584,"best":0.44,"bestCI":0.1946,"lossPot":0.06792,"lossPotCI":0.03423},{"lo":0.5,"hi":0.6,"n":42,"share":0.21,"meanTop":0.5573,"best":0.4286,"bestCI":0.1497,"lossPot":0.04604,"lossPotCI":0.02446},{"lo":0.6,"hi":0.7,"n":51,"share":0.255,"meanTop":0.6496,"best":0.5098,"bestCI":0.1372,"lossPot":0.04408,"lossPotCI":0.01947},{"lo":0.7,"hi":0.8,"n":37,"share":0.185,"meanTop":0.7432,"best":0.6216,"bestCI":0.1563,"lossPot":0.01866,"lossPotCI":0.0128},{"lo":0.8,"hi":0.9,"n":23,"share":0.115,"meanTop":0.8373,"best":0.8696,"bestCI":0.1376,"lossPot":0.00362,"lossPotCI":0.00494},{"lo":0.9,"hi":1,"n":13,"share":0.065,"meanTop":0.9272,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"togethercomputer/tev1-4b-experimental","name":"Together Tev1 4B (exp.)","short":"Tev1","variant":"v2","n":200,"meanTop":0.5087,"best":0.325,"lossPot":0.07423,"ece":0.1944,"buckets":[{"lo":0,"hi":0.4,"n":11,"share":0.055,"meanTop":0.3808,"best":0.1818,"bestCI":0.2279,"lossPot":0.13446,"lossPotCI":0.09308},{"lo":0.4,"hi":0.6,"n":166,"share":0.83,"meanTop":0.4942,"best":0.2952,"bestCI":0.0694,"lossPot":0.07767,"lossPotCI":0.01923},{"lo":0.6,"hi":0.8,"n":22,"share":0.11,"meanTop":0.6658,"best":0.5909,"bestCI":0.2055,"lossPot":0.02151,"lossPotCI":0.0194},{"lo":0.8,"hi":1,"n":1,"share":0.005,"meanTop":0.867,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0}],"curve":[{"lo":0,"hi":0.4,"n":11,"share":0.055,"meanTop":0.3808,"best":0.1818,"bestCI":0.2279,"lossPot":0.13446,"lossPotCI":0.09308},{"lo":0.4,"hi":0.5,"n":91,"share":0.455,"meanTop":0.4495,"best":0.2308,"bestCI":0.0866,"lossPot":0.0779,"lossPotCI":0.02114},{"lo":0.5,"hi":0.6,"n":75,"share":0.375,"meanTop":0.5484,"best":0.3733,"bestCI":0.1095,"lossPot":0.0774,"lossPotCI":0.03414},{"lo":0.6,"hi":0.7,"n":15,"share":0.075,"meanTop":0.6389,"best":0.4667,"bestCI":0.2525,"lossPot":0.02583,"lossPotCI":0.0264},{"lo":0.7,"hi":0.8,"n":7,"share":0.035,"meanTop":0.7235,"best":0.8571,"bestCI":0.2592,"lossPot":0.01224,"lossPotCI":0.02399},{"lo":0.8,"hi":0.9,"n":1,"share":0.005,"meanTop":0.867,"best":1,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]},{"model":"upstage/solar-decide","name":"Upstage Solar Decide","short":"Solar","variant":"v2","n":200,"meanTop":0.5991,"best":0.475,"lossPot":0.05927,"ece":0.1329,"buckets":[{"lo":0,"hi":0.4,"n":3,"share":0.015,"meanTop":0.3755,"best":0.6667,"bestCI":0.5334,"lossPot":0.00468,"lossPotCI":0.00918},{"lo":0.4,"hi":0.6,"n":113,"share":0.565,"meanTop":0.5041,"best":0.469,"bestCI":0.092,"lossPot":0.06993,"lossPotCI":0.02574},{"lo":0.6,"hi":0.8,"n":58,"share":0.29,"meanTop":0.6624,"best":0.3966,"bestCI":0.1259,"lossPot":0.05734,"lossPotCI":0.02896},{"lo":0.8,"hi":1,"n":26,"share":0.13,"meanTop":0.897,"best":0.6538,"bestCI":0.1829,"lossPot":0.02357,"lossPotCI":0.02388}],"curve":[{"lo":0,"hi":0.4,"n":3,"share":0.015,"meanTop":0.3755,"best":0.6667,"bestCI":0.5334,"lossPot":0.00468,"lossPotCI":0.00918},{"lo":0.4,"hi":0.5,"n":51,"share":0.255,"meanTop":0.459,"best":0.451,"bestCI":0.1366,"lossPot":0.06382,"lossPotCI":0.03779},{"lo":0.5,"hi":0.6,"n":62,"share":0.31,"meanTop":0.5412,"best":0.4839,"bestCI":0.1244,"lossPot":0.07496,"lossPotCI":0.03537},{"lo":0.6,"hi":0.7,"n":45,"share":0.225,"meanTop":0.6358,"best":0.4,"bestCI":0.1431,"lossPot":0.05409,"lossPotCI":0.0287},{"lo":0.7,"hi":0.8,"n":13,"share":0.065,"meanTop":0.7544,"best":0.3846,"bestCI":0.2645,"lossPot":0.06856,"lossPotCI":0.08529},{"lo":0.8,"hi":0.9,"n":14,"share":0.07,"meanTop":0.8465,"best":0.6429,"bestCI":0.251,"lossPot":0.03614,"lossPotCI":0.04304},{"lo":0.9,"hi":1,"n":12,"share":0.06,"meanTop":0.956,"best":0.6667,"bestCI":0.2667,"lossPot":0.0089,"lossPotCI":0.0107}]},{"model":"upstage/solar-decide-flash","name":"Upstage Solar Decide Flash","short":"Solar Flash","variant":"v2","n":200,"meanTop":0.5128,"best":0.42,"lossPot":0.07729,"ece":0.0928,"buckets":[{"lo":0,"hi":0.4,"n":1,"share":0.005,"meanTop":0.3837,"best":0,"bestCI":0,"lossPot":0.11778,"lossPotCI":0},{"lo":0.4,"hi":0.6,"n":175,"share":0.875,"meanTop":0.4961,"best":0.4286,"bestCI":0.0733,"lossPot":0.07472,"lossPotCI":0.0225},{"lo":0.6,"hi":0.8,"n":24,"share":0.12,"meanTop":0.6397,"best":0.375,"bestCI":0.1937,"lossPot":0.09437,"lossPotCI":0.08617},{"lo":0.8,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}],"curve":[{"lo":0,"hi":0.4,"n":1,"share":0.005,"meanTop":0.3837,"best":0,"bestCI":0,"lossPot":0.11778,"lossPotCI":0},{"lo":0.4,"hi":0.5,"n":101,"share":0.505,"meanTop":0.4586,"best":0.3465,"bestCI":0.0928,"lossPot":0.07323,"lossPotCI":0.02736},{"lo":0.5,"hi":0.6,"n":74,"share":0.37,"meanTop":0.5474,"best":0.5405,"bestCI":0.1135,"lossPot":0.07676,"lossPotCI":0.03811},{"lo":0.6,"hi":0.7,"n":22,"share":0.11,"meanTop":0.6316,"best":0.4091,"bestCI":0.2055,"lossPot":0.08894,"lossPotCI":0.09231},{"lo":0.7,"hi":0.8,"n":2,"share":0.01,"meanTop":0.7288,"best":0,"bestCI":0,"lossPot":0.15413,"lossPotCI":0.2575},{"lo":0.8,"hi":0.9,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0},{"lo":0.9,"hi":1,"n":0,"share":0,"meanTop":0,"best":0,"bestCI":0,"lossPot":0,"lossPotCI":0}]}]},"agreement":{"definition":"Per suite and variant, decisions answered by every listed core model (≥ 3 of Luna, Jev, Mercury, d1, Clef; free endpoints merged). Plurality of the picks, ties → lowest action index. Sizing share = loss where the chosen and top-EV actions are both bet/raise/all-in of different sizes, ÷ total loss.","core":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna"},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev"},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury"},{"model":"liquid/d1","name":"Liquid d1","short":"d1"},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef"}],"headline":0,"groups":[{"suite":"20261009-160813-rt-n200-s2026","key":"spots","title":"200-spot suite","variant":"v2","decisions":200,"models":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna"},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev"},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury"},{"model":"liquid/d1","name":"Liquid d1","short":"d1"},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef"}],"levels":[{"agree":5,"of":5,"share":0.35,"n":70,"best":0.8,"lossPot":0.00549,"lossPotCI":0.0034},{"agree":4,"of":5,"share":0.285,"n":57,"best":0.807,"lossPot":0.01223,"lossPotCI":0.01039},{"agree":3,"of":5,"share":0.275,"n":55,"best":0.5818,"lossPot":0.04425,"lossPotCI":0.02656},{"agree":2,"of":5,"share":0.09,"n":18,"best":0.6111,"lossPot":0.02536,"lossPotCI":0.02155}],"majority":{"n":200,"best":0.725,"lossPot":0.01986,"lossPotCI":0.00844},"bestModel":"openai/gpt-6-luna-decisions","majorityVsBest":{"n":200,"mean":-0.00587,"ci":0.0099,"sig":false},"players":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","n":200,"best":0.695,"lossPot":0.02573,"lossPotCI":0.01118,"sizingShare":0.3413,"agreesWithMajority":0.77},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev","n":200,"best":0.69,"lossPot":0.02655,"lossPotCI":0.00987,"sizingShare":0.202,"agreesWithMajority":0.9},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","n":200,"best":0.56,"lossPot":0.03243,"lossPotCI":0.00994,"sizingShare":0.2664,"agreesWithMajority":0.695},{"model":"liquid/d1","name":"Liquid d1","short":"d1","n":200,"best":0.65,"lossPot":0.02702,"lossPotCI":0.00791,"sizingShare":0.1119,"agreesWithMajority":0.74},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef","n":200,"best":0.635,"lossPot":0.03464,"lossPotCI":0.01048,"sizingShare":0.0492,"agreesWithMajority":0.79}],"focus":"openai/gpt-6-luna-decisions","focusLossPot":0.02573,"escalation":[{"threshold":0.5,"escalated":0.05,"lossPot":{"cloudflare/clef":0.02132,"inception/mercury-decide":0.02209,"liquid/d1":0.021,"typesafe/jev-1.13":0.02132}},{"threshold":0.55,"escalated":0.13,"lossPot":{"cloudflare/clef":0.02017,"inception/mercury-decide":0.01914,"liquid/d1":0.01782,"typesafe/jev-1.13":0.01989}},{"threshold":0.6,"escalated":0.22,"lossPot":{"cloudflare/clef":0.01666,"inception/mercury-decide":0.01628,"liquid/d1":0.01437,"typesafe/jev-1.13":0.01725}},{"threshold":0.65,"escalated":0.29,"lossPot":{"cloudflare/clef":0.01966,"inception/mercury-decide":0.01797,"liquid/d1":0.01777,"typesafe/jev-1.13":0.01993}},{"threshold":0.7,"escalated":0.345,"lossPot":{"cloudflare/clef":0.02262,"inception/mercury-decide":0.0194,"liquid/d1":0.02065,"typesafe/jev-1.13":0.02029}},{"threshold":0.8,"escalated":0.465,"lossPot":{"cloudflare/clef":0.0227,"inception/mercury-decide":0.02022,"liquid/d1":0.01945,"typesafe/jev-1.13":0.02019}}]},{"suite":"20261009-170429-hands120-cash-n661-s31-dev","key":"cash-hands-dev","title":"Cash 100bb hands · dev","variant":"v2","decisions":200,"models":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna"},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev"},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury"},{"model":"liquid/d1","name":"Liquid d1","short":"d1"}],"levels":[{"agree":4,"of":4,"share":0.435,"n":87,"best":0.7931,"lossPot":0.01752,"lossPotCI":0.01322},{"agree":3,"of":4,"share":0.455,"n":91,"best":0.7582,"lossPot":0.02039,"lossPotCI":0.01187},{"agree":2,"of":4,"share":0.11,"n":22,"best":0.5909,"lossPot":0.14879,"lossPotCI":0.1468}],"majority":{"n":200,"best":0.755,"lossPot":0.03327,"lossPotCI":0.01854},"bestModel":"typesafe/jev-1.13","majorityVsBest":{"n":200,"mean":0.00918,"ci":0.01291,"sig":false},"players":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","n":200,"best":0.77,"lossPot":0.03202,"lossPotCI":0.0176,"sizingShare":0,"agreesWithMajority":0.8},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev","n":200,"best":0.745,"lossPot":0.02409,"lossPotCI":0.00999,"sizingShare":0.0185,"agreesWithMajority":0.885},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","n":200,"best":0.655,"lossPot":0.04612,"lossPotCI":0.01485,"sizingShare":0.0004,"agreesWithMajority":0.725},{"model":"liquid/d1","name":"Liquid d1","short":"d1","n":200,"best":0.765,"lossPot":0.03143,"lossPotCI":0.01827,"sizingShare":0.0005,"agreesWithMajority":0.915}],"focus":"openai/gpt-6-luna-decisions","focusLossPot":0.03202,"escalation":[{"threshold":0.5,"escalated":0.01,"lossPot":{"inception/mercury-decide":0.02716,"liquid/d1":0.03202,"typesafe/jev-1.13":0.02716}},{"threshold":0.55,"escalated":0.04,"lossPot":{"inception/mercury-decide":0.02604,"liquid/d1":0.02969,"typesafe/jev-1.13":0.02484}},{"threshold":0.6,"escalated":0.1,"lossPot":{"inception/mercury-decide":0.02803,"liquid/d1":0.03253,"typesafe/jev-1.13":0.02683}},{"threshold":0.65,"escalated":0.19,"lossPot":{"inception/mercury-decide":0.02666,"liquid/d1":0.03103,"typesafe/jev-1.13":0.02194}},{"threshold":0.7,"escalated":0.28,"lossPot":{"inception/mercury-decide":0.03148,"liquid/d1":0.0318,"typesafe/jev-1.13":0.02266}},{"threshold":0.8,"escalated":0.465,"lossPot":{"inception/mercury-decide":0.03634,"liquid/d1":0.03393,"typesafe/jev-1.13":0.02482}}]},{"suite":"20261009-170429-hands120-cash-n661-s31-test","key":"cash-hands-test","title":"Cash 100bb hands · test","variant":"nuts","decisions":324,"models":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna"},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury"},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef"}],"levels":[{"agree":3,"of":3,"share":0.7006,"n":227,"best":0.815,"lossPot":0.01133,"lossPotCI":0.00688},{"agree":2,"of":3,"share":0.2994,"n":97,"best":0.7216,"lossPot":0.0239,"lossPotCI":0.01533}],"majority":{"n":324,"best":0.787,"lossPot":0.0151,"lossPotCI":0.00667},"bestModel":"openai/gpt-6-luna-decisions","majorityVsBest":{"n":324,"mean":-0.00014,"ci":0.00493,"sig":false},"players":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","n":324,"best":0.784,"lossPot":0.01523,"lossPotCI":0.00619,"sizingShare":0.1009,"agreesWithMajority":0.8889},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","n":324,"best":0.7562,"lossPot":0.02276,"lossPotCI":0.00824,"sizingShare":0.1409,"agreesWithMajority":0.8735},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef","n":324,"best":0.784,"lossPot":0.01691,"lossPotCI":0.00719,"sizingShare":0.0992,"agreesWithMajority":0.9383}],"focus":"openai/gpt-6-luna-decisions","focusLossPot":0.01523,"escalation":[{"threshold":0.5,"escalated":0,"lossPot":{"cloudflare/clef":0.01523,"inception/mercury-decide":0.01523}},{"threshold":0.55,"escalated":0.0247,"lossPot":{"cloudflare/clef":0.01556,"inception/mercury-decide":0.01695}},{"threshold":0.6,"escalated":0.0864,"lossPot":{"cloudflare/clef":0.01565,"inception/mercury-decide":0.01704}},{"threshold":0.65,"escalated":0.1389,"lossPot":{"cloudflare/clef":0.01621,"inception/mercury-decide":0.01793}},{"threshold":0.7,"escalated":0.216,"lossPot":{"cloudflare/clef":0.01529,"inception/mercury-decide":0.01925}},{"threshold":0.8,"escalated":0.3426,"lossPot":{"cloudflare/clef":0.01632,"inception/mercury-decide":0.0185}}]},{"suite":"20261009-170429-hands120-cash-n661-s31-test","key":"cash-hands-test","title":"Cash 100bb hands · test","variant":"v2","decisions":324,"models":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna"},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury"},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef"}],"levels":[{"agree":3,"of":3,"share":0.4475,"n":145,"best":0.8138,"lossPot":0.01708,"lossPotCI":0.0111},{"agree":2,"of":3,"share":0.5494,"n":178,"best":0.7079,"lossPot":0.02966,"lossPotCI":0.01267},{"agree":1,"of":3,"share":0.0031,"n":1,"best":0,"lossPot":0.00432,"lossPotCI":0}],"majority":{"n":324,"best":0.7531,"lossPot":0.02395,"lossPotCI":0.00857},"bestModel":"openai/gpt-6-luna-decisions","majorityVsBest":{"n":324,"mean":0.00202,"ci":0.00802,"sig":false},"players":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","n":324,"best":0.7994,"lossPot":0.02193,"lossPotCI":0.00848,"sizingShare":0.0701,"agreesWithMajority":0.8025},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","n":324,"best":0.6451,"lossPot":0.04281,"lossPotCI":0.01051,"sizingShare":0.055,"agreesWithMajority":0.7284},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef","n":324,"best":0.7377,"lossPot":0.03102,"lossPotCI":0.00993,"sizingShare":0.0552,"agreesWithMajority":0.9136}],"focus":"openai/gpt-6-luna-decisions","focusLossPot":0.02193,"escalation":[{"threshold":0.5,"escalated":0.0062,"lossPot":{"cloudflare/clef":0.02104,"inception/mercury-decide":0.02104}},{"threshold":0.55,"escalated":0.0617,"lossPot":{"cloudflare/clef":0.02168,"inception/mercury-decide":0.0209}},{"threshold":0.6,"escalated":0.1389,"lossPot":{"cloudflare/clef":0.02023,"inception/mercury-decide":0.02097}},{"threshold":0.65,"escalated":0.1883,"lossPot":{"cloudflare/clef":0.0208,"inception/mercury-decide":0.02202}},{"threshold":0.7,"escalated":0.2623,"lossPot":{"cloudflare/clef":0.02435,"inception/mercury-decide":0.02623}},{"threshold":0.8,"escalated":0.4506,"lossPot":{"cloudflare/clef":0.02771,"inception/mercury-decide":0.03336}}]},{"suite":"20261009-173433-hands60-mtt20-n300-s33","key":"mtt20-hands","title":"MTT 20bb hands","variant":"nuts","decisions":300,"models":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna"},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev"},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury"},{"model":"liquid/d1","name":"Liquid d1","short":"d1"},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef"}],"levels":[{"agree":5,"of":5,"share":0.6533,"n":196,"best":0.7959,"lossPot":0.01085,"lossPotCI":0.00642},{"agree":4,"of":5,"share":0.2067,"n":62,"best":0.629,"lossPot":0.03326,"lossPotCI":0.01779},{"agree":3,"of":5,"share":0.14,"n":42,"best":0.6667,"lossPot":0.03589,"lossPotCI":0.04473}],"majority":{"n":300,"best":0.7433,"lossPot":0.01898,"lossPotCI":0.00842},"bestModel":"liquid/d1","majorityVsBest":{"n":300,"mean":0.00108,"ci":0.00292,"sig":false},"players":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","n":300,"best":0.7633,"lossPot":0.01862,"lossPotCI":0.00855,"sizingShare":0.0229,"agreesWithMajority":0.87},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev","n":300,"best":0.6833,"lossPot":0.0242,"lossPotCI":0.00728,"sizingShare":0.0524,"agreesWithMajority":0.8533},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","n":300,"best":0.74,"lossPot":0.02089,"lossPotCI":0.00878,"sizingShare":0.0336,"agreesWithMajority":0.9367},{"model":"liquid/d1","name":"Liquid d1","short":"d1","n":300,"best":0.7467,"lossPot":0.0179,"lossPotCI":0.00821,"sizingShare":0.0708,"agreesWithMajority":0.96},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef","n":300,"best":0.76,"lossPot":0.01842,"lossPotCI":0.00663,"sizingShare":0.0981,"agreesWithMajority":0.8933}],"focus":"openai/gpt-6-luna-decisions","focusLossPot":0.01862,"escalation":[{"threshold":0.5,"escalated":0.0033,"lossPot":{"cloudflare/clef":0.01772,"inception/mercury-decide":0.01772,"liquid/d1":0.01772,"typesafe/jev-1.13":0.01772}},{"threshold":0.55,"escalated":0.0333,"lossPot":{"cloudflare/clef":0.01757,"inception/mercury-decide":0.01761,"liquid/d1":0.01761,"typesafe/jev-1.13":0.01762}},{"threshold":0.6,"escalated":0.0667,"lossPot":{"cloudflare/clef":0.0175,"inception/mercury-decide":0.0179,"liquid/d1":0.0176,"typesafe/jev-1.13":0.01791}},{"threshold":0.65,"escalated":0.1233,"lossPot":{"cloudflare/clef":0.01783,"inception/mercury-decide":0.01974,"liquid/d1":0.01758,"typesafe/jev-1.13":0.01977}},{"threshold":0.7,"escalated":0.1967,"lossPot":{"cloudflare/clef":0.01759,"inception/mercury-decide":0.01953,"liquid/d1":0.01736,"typesafe/jev-1.13":0.02026}},{"threshold":0.8,"escalated":0.3333,"lossPot":{"cloudflare/clef":0.0182,"inception/mercury-decide":0.01982,"liquid/d1":0.01698,"typesafe/jev-1.13":0.0214}}]},{"suite":"20261009-173433-hands60-mtt20-n300-s33","key":"mtt20-hands","title":"MTT 20bb hands","variant":"v2","decisions":300,"models":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna"},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev"},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury"},{"model":"liquid/d1","name":"Liquid d1","short":"d1"},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef"}],"levels":[{"agree":5,"of":5,"share":0.4233,"n":127,"best":0.811,"lossPot":0.01192,"lossPotCI":0.00718},{"agree":4,"of":5,"share":0.34,"n":102,"best":0.6765,"lossPot":0.03432,"lossPotCI":0.0216},{"agree":3,"of":5,"share":0.2367,"n":71,"best":0.5634,"lossPot":0.0463,"lossPotCI":0.02577}],"majority":{"n":300,"best":0.7067,"lossPot":0.02767,"lossPotCI":0.01011},"bestModel":"liquid/d1","majorityVsBest":{"n":300,"mean":0.00371,"ci":0.00543,"sig":false},"players":[{"model":"openai/gpt-6-luna-decisions","name":"GPT-6 Luna Decisions","short":"Luna","n":300,"best":0.74,"lossPot":0.02488,"lossPotCI":0.00967,"sizingShare":0.0007,"agreesWithMajority":0.7733},{"model":"typesafe/jev-1.13","name":"TypeSafe Jev 1.13","short":"Jev","n":300,"best":0.6833,"lossPot":0.0271,"lossPotCI":0.00966,"sizingShare":0.0408,"agreesWithMajority":0.8667},{"model":"inception/mercury-decide","name":"Inception Mercury Decide","short":"Mercury","n":300,"best":0.6333,"lossPot":0.03708,"lossPotCI":0.01034,"sizingShare":0.0392,"agreesWithMajority":0.8},{"model":"liquid/d1","name":"Liquid d1","short":"d1","n":300,"best":0.7267,"lossPot":0.02396,"lossPotCI":0.00932,"sizingShare":0.0462,"agreesWithMajority":0.92},{"model":"cloudflare/clef","name":"Cloudflare Clef","short":"Clef","n":300,"best":0.68,"lossPot":0.03353,"lossPotCI":0.00963,"sizingShare":0.0572,"agreesWithMajority":0.8267}],"focus":"openai/gpt-6-luna-decisions","focusLossPot":0.02488,"escalation":[{"threshold":0.5,"escalated":0.01,"lossPot":{"cloudflare/clef":0.02488,"inception/mercury-decide":0.02488,"liquid/d1":0.02488,"typesafe/jev-1.13":0.02488}},{"threshold":0.55,"escalated":0.0467,"lossPot":{"cloudflare/clef":0.02479,"inception/mercury-decide":0.02459,"liquid/d1":0.02189,"typesafe/jev-1.13":0.02231}},{"threshold":0.6,"escalated":0.0967,"lossPot":{"cloudflare/clef":0.02624,"inception/mercury-decide":0.02299,"liquid/d1":0.02137,"typesafe/jev-1.13":0.02292}},{"threshold":0.65,"escalated":0.1633,"lossPot":{"cloudflare/clef":0.02676,"inception/mercury-decide":0.0231,"liquid/d1":0.0213,"typesafe/jev-1.13":0.02364}},{"threshold":0.7,"escalated":0.2133,"lossPot":{"cloudflare/clef":0.02767,"inception/mercury-decide":0.02498,"liquid/d1":0.02287,"typesafe/jev-1.13":0.02558}},{"threshold":0.8,"escalated":0.42,"lossPot":{"cloudflare/clef":0.02442,"inception/mercury-decide":0.02756,"liquid/d1":0.02216,"typesafe/jev-1.13":0.02586}}]}]}}