{"schemaVersion":1,"writing":{"title":"Creative Writing","metric":{"name":"Thurstone comparison score","scale":"Relative to the rated pool (centred at 0); higher is better","interval":"95% bootstrap interval, 300 resamples of stories and evaluators","count":"Matched story pairs compared","winChance":"Average fitted probability of beating another model in the pool"},"description":"Writer models answer the same constrained creative briefs. Separate evaluator models read matched stories in both orders and judge which is better; pairwise judgments are fitted with a Thurstone model and a correction for presentation order.","sourceUrl":"https://github.com/lechmazur/writing","readmeUrl":"https://github.com/lechmazur/writing/blob/994504ef5e7ee59713c31a08b761de6ec1bcc188/README.md","dataUrl":"https://github.com/lechmazur/writing/tree/994504ef5e7ee59713c31a08b761de6ec1bcc188/data/writing_mistral_large4_20261007","snapshotDate":"2026-10-07","sourceCommit":"994504ef5e7ee59713c31a08b761de6ec1bcc188","sourceCommitDate":"2026-10-08T13:14:17-04:00","sourceFiles":{"README.md":"d9537bb0ef7ffa75","data/writing_mistral_large4_20261007/ratings.csv":"48d96ed3aa20a5e3","data/writing_mistral_large4_20261007/pair_stats.csv":"9d5c9138c5a1fa42"},"totals":{"models":57,"directPairings":934,"storyPairs":15692,"judgments":105704},"notes":["Only completed stories were compared. 6 models completed fewer stories than planned; their story coverage is listed with their results.","Intervals reflect variation in completed comparisons, not the effect of missing stories or judgments."],"models":[{"id":"claude-opus-5-xhigh","name":"Claude Opus 5 (xhigh)","rank":1,"score":3.777,"low":3.722,"high":3.839,"winChance":0.932,"count":1002,"opponents":56},{"id":"claude-fable-5-1-high","name":"Claude Fable 5.1 (high)","rank":2,"score":3.76,"low":3.675,"high":3.86,"winChance":0.931,"count":437,"opponents":30},{"id":"claude-opus-5-5-high","name":"Claude Opus 5.5 (high)","rank":3,"score":3.718,"low":3.63,"high":3.81,"winChance":0.929,"count":436,"opponents":26},{"id":"gpt-6-astra-high","name":"GPT-6 Astra (high)","rank":4,"score":3.461,"low":3.388,"high":3.535,"winChance":0.911,"count":860,"opponents":56},{"id":"claude-opus-5-high","name":"Claude Opus 5 (high)","rank":5,"score":3.414,"low":3.313,"high":3.531,"winChance":0.908,"count":347,"opponents":26},{"id":"glm-5.3","name":"GLM-5.3 (max)","rank":6,"score":3.025,"low":2.928,"high":3.113,"winChance":0.877,"count":390,"opponents":32},{"id":"claude-fable-5-high","name":"Claude Fable 5 (high)","rank":7,"score":2.901,"low":2.838,"high":2.974,"winChance":0.866,"coverage":{"completed":395,"planned":400,"unit":"stories"},"count":890,"opponents":42},{"id":"gpt-5.6-xhigh","name":"GPT-5.6 Sol (xhigh)","rank":8,"score":2.519,"low":2.452,"high":2.6,"winChance":0.83,"count":740,"opponents":38},{"id":"gpt-5.5-xhigh","name":"GPT-5.5 (xhigh)","rank":9,"score":2.482,"low":2.415,"high":2.565,"winChance":0.827,"count":996,"opponents":41},{"id":"kimi-k3","name":"Kimi K3","rank":10,"score":2.469,"low":2.387,"high":2.546,"winChance":0.825,"count":905,"opponents":45},{"id":"gpt-5.6-high","name":"GPT-5.6 Sol (high)","rank":11,"score":2.329,"low":2.25,"high":2.409,"winChance":0.811,"count":790,"opponents":38},{"id":"gpt-5.4-medium","name":"GPT-5.4 (medium)","rank":12,"score":2.018,"low":1.896,"high":2.149,"winChance":0.777,"count":361,"opponents":19},{"id":"gpt-5.4-xhigh","name":"GPT-5.4 (xhigh)","rank":13,"score":2.012,"low":1.905,"high":2.134,"winChance":0.776,"count":431,"opponents":21},{"id":"claude-opus-4-7-adaptive","name":"Claude Opus 4.7 (high)","rank":14,"score":1.815,"low":1.696,"high":1.923,"winChance":0.753,"coverage":{"completed":347,"planned":400,"unit":"stories"},"count":585,"opponents":31},{"id":"claude-sonnet-4-6-16K","name":"Claude Sonnet 4.6 Thinking 16K","rank":15,"score":1.705,"low":1.611,"high":1.812,"winChance":0.74,"count":577,"opponents":34},{"id":"mimo-v2.6-pro","name":"Xiaomi MiMo V2.6 Pro (thinking)","rank":16,"score":1.617,"low":1.469,"high":1.754,"winChance":0.729,"coverage":{"completed":375,"planned":400,"unit":"stories"},"count":383,"opponents":26},{"id":"claude-opus-4-6-16K","name":"Claude Opus 4.6 Thinking 16K","rank":17,"score":1.178,"low":0.995,"high":1.338,"winChance":0.673,"count":235,"opponents":17},{"id":"claude-opus-4-8-xhigh","name":"Claude Opus 4.8 (xhigh)","rank":18,"score":0.808,"low":0.71,"high":0.91,"winChance":0.622,"count":680,"opponents":32},{"id":"muse-spark-1.1-high","name":"Muse Spark 1.1 (high)","rank":19,"score":0.804,"low":0.714,"high":0.91,"winChance":0.621,"count":600,"opponents":27},{"id":"muse-spark-1.3-high","name":"Muse Spark 1.3 (high)","rank":20,"score":0.624,"low":0.539,"high":0.718,"winChance":0.595,"count":835,"opponents":56},{"id":"deepseek-v4-pro-high","name":"DeepSeek V4 Pro (high)","rank":21,"score":0.59,"low":0.483,"high":0.72,"winChance":0.59,"count":525,"opponents":32},{"id":"glm-5.2-max","name":"GLM-5.2 (max)","rank":22,"score":0.505,"low":0.419,"high":0.6,"winChance":0.578,"count":817,"opponents":38},{"id":"grok-4.7-high","name":"Grok 4.7 (high)","rank":23,"score":0.444,"low":0.236,"high":0.641,"winChance":0.569,"count":416,"opponents":26},{"id":"gpt-5.2-medium","name":"GPT-5.2 (medium)","rank":24,"score":0.383,"low":0.214,"high":0.546,"winChance":0.56,"count":229,"opponents":18},{"id":"claude-opus-4-8-high","name":"Claude Opus 4.8 (high)","rank":25,"score":0.294,"low":0.204,"high":0.397,"winChance":0.547,"coverage":{"completed":399,"planned":400,"unit":"stories"},"count":625,"opponents":32},{"id":"gemini-3.8-flash-high","name":"Gemini 3.8 Flash (high)","rank":26,"score":0.266,"low":0.139,"high":0.401,"winChance":0.542,"count":375,"opponents":26},{"id":"qwen3.8-max","name":"Qwen 3.8 Max","rank":27,"score":0.258,"low":0.137,"high":0.368,"winChance":0.541,"coverage":{"completed":398,"planned":400,"unit":"stories"},"count":525,"opponents":32},{"id":"kimi-k2.6","name":"Kimi K2.6","rank":28,"score":0.128,"low":0.028,"high":0.235,"winChance":0.522,"count":849,"opponents":38},{"id":"muse-spark-1.2-high","name":"Muse Spark 1.2 (high)","rank":29,"score":0.0,"low":-0.091,"high":0.102,"winChance":0.502,"count":700,"opponents":49},{"id":"minimax-m3","name":"MiniMax-M3","rank":30,"score":-0.013,"low":-0.136,"high":0.117,"winChance":0.5,"count":816,"opponents":44},{"id":"mistral-medium-2508","name":"Mistral Medium 3.1","rank":31,"score":-0.335,"low":-0.453,"high":-0.192,"winChance":0.451,"count":534,"opponents":31},{"id":"deepseek-v4.1-flash-high","name":"DeepSeek V4.1 Flash (high)","rank":32,"score":-0.407,"low":-0.529,"high":-0.273,"winChance":0.441,"count":392,"opponents":26},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro Preview","rank":33,"score":-0.49,"low":-0.591,"high":-0.384,"winChance":0.428,"count":753,"opponents":38},{"id":"qwen3.8-27b","name":"Qwen3.8-27B","rank":34,"score":-0.562,"low":-0.742,"high":-0.393,"winChance":0.417,"coverage":{"completed":389,"planned":400,"unit":"stories"},"count":233,"opponents":32},{"id":"mimo-v2.5-pro","name":"Xiaomi MiMo V2.5 Pro","rank":35,"score":-0.628,"low":-0.765,"high":-0.48,"winChance":0.407,"count":869,"opponents":50},{"id":"qwen3-max-preview","name":"Qwen 3 Max Preview","rank":36,"score":-0.64,"low":-0.808,"high":-0.491,"winChance":0.406,"count":227,"opponents":19},{"id":"gemini-3.7-flash-high","name":"Gemini 3.7 Flash (high)","rank":37,"score":-0.653,"low":-0.748,"high":-0.537,"winChance":0.404,"count":393,"opponents":32},{"id":"qwen3.6-max-preview","name":"Qwen 3.6 Max Preview","rank":38,"score":-0.893,"low":-1.018,"high":-0.754,"winChance":0.368,"count":475,"opponents":25},{"id":"glm-5.1","name":"GLM-5.1","rank":39,"score":-0.996,"low":-1.184,"high":-0.831,"winChance":0.353,"count":438,"opponents":26},{"id":"kimi-k2.5","name":"Kimi K2.5 Thinking","rank":40,"score":-1.039,"low":-1.203,"high":-0.853,"winChance":0.347,"count":233,"opponents":16},{"id":"mimo-v2-pro","name":"Xiaomi MiMo V2 Pro","rank":41,"score":-1.178,"low":-1.413,"high":-0.945,"winChance":0.327,"count":263,"opponents":17},{"id":"ernie-5.1","name":"Baidu Ernie 5.1","rank":42,"score":-1.198,"low":-1.348,"high":-1.058,"winChance":0.324,"count":628,"opponents":43},{"id":"mistral-large-4-high","name":"Mistral Large 4 (high)","rank":43,"score":-1.585,"low":-1.698,"high":-1.458,"winChance":0.271,"count":520,"opponents":26},{"id":"mistral-large-2512","name":"Mistral Large 3","rank":44,"score":-1.72,"low":-1.836,"high":-1.603,"winChance":0.254,"count":426,"opponents":34},{"id":"gemma-4-31b-it-reasoning","name":"Gemma 4 31B Reasoning","rank":45,"score":-1.84,"low":-1.941,"high":-1.742,"winChance":0.239,"count":445,"opponents":35},{"id":"seed-2.0-pro","name":"ByteDance Seed2.0 Pro","rank":46,"score":-1.936,"low":-2.06,"high":-1.802,"winChance":0.227,"count":655,"opponents":47},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","rank":47,"score":-1.939,"low":-2.043,"high":-1.843,"winChance":0.227,"count":832,"opponents":41},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","rank":48,"score":-2.139,"low":-2.251,"high":-2.027,"winChance":0.204,"count":663,"opponents":47},{"id":"qwen3.6-plus","name":"Qwen 3.6 Plus","rank":49,"score":-2.232,"low":-2.406,"high":-2.053,"winChance":0.193,"count":125,"opponents":10},{"id":"mistral-medium-3.5","name":"Mistral Medium 3.5","rank":50,"score":-2.509,"low":-2.635,"high":-2.379,"winChance":0.164,"count":599,"opponents":43},{"id":"qwen3.7-max","name":"Qwen 3.7 Max","rank":51,"score":-2.614,"low":-2.748,"high":-2.485,"winChance":0.154,"count":598,"opponents":31},{"id":"deepseek-v32","name":"DeepSeek V3.2","rank":52,"score":-2.829,"low":-3.075,"high":-2.565,"winChance":0.134,"count":232,"opponents":15},{"id":"grok-4.6-high","name":"Grok 4.6 (high)","rank":53,"score":-2.833,"low":-2.967,"high":-2.678,"winChance":0.134,"count":436,"opponents":31},{"id":"gpt-oss-120b","name":"GPT-OSS-120B","rank":54,"score":-3.13,"low":-3.249,"high":-3.006,"winChance":0.109,"count":394,"opponents":31},{"id":"minimax-m2.7","name":"MiniMax-M2.7","rank":55,"score":-3.719,"low":-3.845,"high":-3.573,"winChance":0.069,"count":409,"opponents":27},{"id":"grok-4.3","name":"Grok 4.3","rank":56,"score":-4.208,"low":-4.376,"high":-4.025,"winChance":0.044,"count":406,"opponents":24},{"id":"grok-4.5-high","name":"Grok 4.5 (high)","rank":57,"score":-5.04,"low":-5.135,"high":-4.956,"winChance":0.017,"count":849,"opponents":43}],"pairs":{"kind":"observed","fields":["a","b","storyPairs","aScoreFromMargin","aScoreCi95HalfWidth","aMeanSignedMargin"],"description":"Observed direct comparisons; a and b index models[]. Not fitted probabilities.","rows":[[0,56,10,1.0,0.0,7.225],[7,56,20,1.0,0.0,7.037],[0,53,13,1.0,0.0,6.542],[1,53,8,1.0,0.0,6.497],[16,56,20,1.0,0.0,6.445],[3,56,5,1.0,0.0,6.324],[10,56,20,1.0,0.0,6.309],[13,55,20,1.0,0.0,6.295],[13,56,20,1.0,0.0,6.25],[6,55,20,1.0,0.0,6.157],[0,55,5,1.0,0.0,6.085],[3,54,5,1.0,0.0,6.003],[0,51,5,1.0,0.0,5.987],[11,56,20,1.0,0.0,5.977],[8,56,20,1.0,0.0,5.94],[0,50,10,1.0,0.0,5.908],[6,56,20,1.0,0.0,5.85],[3,49,20,1.0,0.0,5.831],[14,50,6,1.0,0.0,5.767],[4,52,3,1.0,0.0,5.728],[5,52,5,1.0,0.0,5.727],[6,53,20,1.0,0.0,5.712],[13,54,8,1.0,0.0,5.669],[10,53,20,1.0,0.0,5.654],[3,55,5,1.0,0.0,5.653],[1,34,5,1.0,0.0,5.64],[3,50,5,1.0,0.0,5.585],[5,53,5,1.0,0.0,5.526],[1,45,5,1.0,0.0,5.52],[7,52,20,1.0,0.0,5.469],[17,56,20,1.0,0.0,5.458],[2,53,3,1.0,0.0,5.444],[2,52,3,1.0,0.0,5.444],[8,53,20,1.0,0.0,5.439],[3,48,5,1.0,0.0,5.419],[5,49,5,1.0,0.0,5.41],[32,55,20,1.0,0.0,5.384],[1,49,5,1.0,0.0,5.378],[14,55,6,1.0,0.0,5.375],[38,56,20,1.0,0.0,5.373],[23,56,20,1.0,0.0,5.357],[8,55,20,1.0,0.0,5.357],[24,55,20,1.0,0.0,5.333],[32,56,20,1.0,0.0,5.326],[6,54,20,1.0,0.0,5.326],[12,56,20,1.0,0.0,5.323],[8,54,8,1.0,0.0,5.276],[0,54,5,1.0,0.0,5.267],[6,52,20,1.0,0.0,5.241],[4,53,3,1.0,0.0,5.222],[14,56,20,1.0,0.0,5.149],[0,44,5,1.0,0.0,5.077],[1,52,5,1.0,0.0,5.05],[2,34,3,1.0,0.0,5.022],[0,45,5,1.0,0.0,4.971],[24,56,20,1.0,0.0,4.945],[20,53,5,1.0,0.0,4.933],[0,43,5,1.0,0.0,4.933],[0,52,20,1.0,0.0,4.927],[10,52,20,1.0,0.0,4.886],[10,50,20,1.0,0.0,4.877],[6,50,20,1.0,0.0,4.867],[10,49,20,1.0,0.0,4.851],[14,49,6,1.0,0.0,4.836],[7,50,20,1.0,0.0,4.818],[9,50,15,1.0,0.0,4.798],[4,45,3,1.0,0.0,4.75],[0,41,13,1.0,0.0,4.734],[17,55,20,1.0,0.0,4.716],[13,49,20,1.0,0.0,4.716],[4,49,3,1.0,0.0,4.711],[5,43,5,1.0,0.0,4.71],[1,33,5,1.0,0.0,4.709],[27,54,8,1.0,0.0,4.708],[17,53,20,1.0,0.0,4.708],[3,52,20,1.0,0.0,4.698],[3,53,20,1.0,0.0,4.678],[3,37,5,1.0,0.0,4.64],[0,38,10,1.0,0.0,4.612],[1,29,8,1.0,0.0,4.604],[6,48,20,1.0,0.0,4.556],[0,47,8,1.0,0.0,4.556],[4,41,3,1.0,0.0,4.544],[21,56,20,1.0,0.0,4.504],[2,45,3,1.0,0.0,4.5],[1,43,5,1.0,0.0,4.463],[0,48,5,1.0,0.0,4.462],[7,53,20,1.0,0.0,4.45],[21,55,20,1.0,0.0,4.436],[0,37,10,1.0,0.0,4.433],[2,49,3,1.0,0.0,4.428],[3,42,20,1.0,0.0,4.412],[0,27,20,1.0,0.0,4.404],[6,41,20,1.0,0.0,4.396],[2,29,3,1.0,0.0,4.394],[6,46,20,1.0,0.0,4.39],[4,34,3,1.0,0.0,4.389],[3,43,20,1.0,0.0,4.383],[24,53,20,1.0,0.0,4.374],[0,33,5,1.0,0.0,4.372],[1,44,5,1.0,0.0,4.367],[1,47,8,1.0,0.0,4.352],[13,45,8,1.0,0.0,4.288],[1,42,20,1.0,0.0,4.282],[15,49,3,1.0,0.0,4.278],[9,49,15,1.0,0.0,4.27],[2,41,3,1.0,0.0,4.267],[3,33,20,1.0,0.0,4.264],[21,53,20,1.0,0.0,4.259],[4,47,3,1.0,0.0,4.239],[6,43,20,1.0,0.0,4.239],[17,49,20,1.0,0.0,4.221],[12,34,20,1.0,0.0,4.211],[0,42,20,1.0,0.0,4.206],[2,31,20,1.0,0.0,4.195],[0,30,20,1.0,0.0,4.189],[21,52,20,1.0,0.0,4.188],[0,35,10,1.0,0.0,4.177],[4,42,20,1.0,0.0,4.177],[4,44,3,1.0,0.0,4.156],[2,44,3,1.0,0.0,4.156],[10,43,20,1.0,0.0,4.154],[0,34,10,1.0,0.0,4.15],[3,18,5,1.0,0.0,4.15],[47,56,20,1.0,0.0,4.139],[1,41,8,1.0,0.0,4.133],[3,45,5,1.0,0.0,4.131],[0,49,5,1.0,0.0,4.12],[5,42,20,1.0,0.0,4.119],[10,33,5,1.0,0.0,4.117],[9,33,5,1.0,0.0,4.117],[0,46,10,1.0,0.0,4.113],[1,31,20,1.0,0.0,4.112],[24,54,20,1.0,0.0,4.112],[13,50,20,1.0,0.0,4.105],[2,42,20,1.0,0.0,4.103],[6,47,20,1.0,0.0,4.095],[13,47,8,1.0,0.0,4.078],[0,40,10,1.0,0.0,4.071],[8,45,20,1.0,0.0,4.062],[2,47,3,1.0,0.0,4.044],[17,54,20,1.0,0.0,4.039],[3,29,30,1.0,0.0,4.035],[6,20,20,1.0,0.0,4.018],[0,29,23,1.0,0.0,4.017],[20,49,5,1.0,0.0,4.017],[8,43,20,1.0,0.0,4.002],[20,45,5,1.0,0.0,4.0],[1,26,5,1.0,0.0,3.99],[7,49,20,1.0,0.0,3.971],[15,45,4,1.0,0.0,3.962],[6,49,20,1.0,0.0,3.961],[3,30,5,1.0,0.0,3.96],[28,50,5,1.0,0.0,3.95],[1,28,25,1.0,0.0,3.92],[8,30,20,1.0,0.0,3.908],[2,43,3,1.0,0.0,3.906],[21,54,20,1.0,0.0,3.901],[8,50,20,1.0,0.0,3.884],[0,23,20,1.0,0.0,3.882],[0,32,20,1.0,0.0,3.862],[5,34,5,1.0,0.0,3.843],[2,33,3,1.0,0.0,3.822],[6,29,20,1.0,0.0,3.819],[0,20,20,1.0,0.0,3.813],[14,47,8,1.0,0.0,3.805],[4,31,20,1.0,0.0,3.805],[8,49,20,1.0,0.0,3.804],[6,45,20,1.0,0.0,3.797],[36,53,5,1.0,0.0,3.79],[5,33,5,1.0,0.0,3.78],[25,53,4,1.0,0.0,3.771],[9,43,20,1.0,0.0,3.766],[0,19,25,1.0,0.0,3.753],[21,50,20,1.0,0.0,3.741],[0,31,20,1.0,0.0,3.741],[4,43,3,1.0,0.0,3.733],[1,36,5,1.0,0.0,3.717],[6,36,20,1.0,0.0,3.716],[17,45,20,1.0,0.0,3.711],[6,28,25,1.0,0.0,3.704],[0,36,20,1.0,0.0,3.702],[14,46,20,1.0,0.0,3.695],[46,56,20,1.0,0.0,3.692],[17,48,20,1.0,0.0,3.684],[0,39,10,1.0,0.0,3.667],[44,56,20,1.0,0.0,3.662],[17,44,20,1.0,0.0,3.655],[12,39,20,1.0,0.0,3.646],[15,43,4,1.0,0.0,3.633],[0,26,20,1.0,0.0,3.631],[22,49,5,1.0,0.0,3.63],[19,50,5,1.0,0.0,3.63],[7,43,20,1.0,0.0,3.624],[3,34,20,1.0,0.0,3.618],[17,50,20,1.0,0.0,3.616],[14,34,20,1.0,0.0,3.612],[9,42,20,1.0,0.0,3.606],[20,43,5,1.0,0.0,3.59],[3,39,5,1.0,0.0,3.58],[27,45,8,1.0,0.0,3.575],[3,40,5,1.0,0.0,3.566],[5,26,5,1.0,0.0,3.557],[7,34,20,1.0,0.0,3.548],[8,39,20,1.0,0.0,3.541],[8,40,20,1.0,0.0,3.54],[2,20,20,1.0,0.0,3.539],[11,37,10,1.0,0.0,3.526],[6,44,20,1.0,0.0,3.516],[17,43,20,1.0,0.0,3.513],[7,45,20,1.0,0.0,3.501],[13,37,30,1.0,0.0,3.5],[1,22,20,1.0,0.0,3.498],[2,25,20,1.0,0.0,3.493],[53,56,20,1.0,0.0,3.492],[31,53,6,1.0,0.0,3.478],[6,33,5,1.0,0.0,3.47],[10,45,20,1.0,0.0,3.456],[3,19,30,1.0,0.0,3.45],[20,52,20,1.0,0.0,3.448],[24,45,20,1.0,0.0,3.438],[2,26,20,1.0,0.0,3.438],[3,22,20,1.0,0.0,3.435],[2,36,3,1.0,0.0,3.433],[6,32,20,1.0,0.0,3.431],[4,25,20,1.0,0.0,3.429],[9,45,15,1.0,0.0,3.427],[3,35,5,1.0,0.0,3.399],[4,36,3,1.0,0.0,3.394],[13,46,20,1.0,0.0,3.394],[0,22,20,1.0,0.0,3.384],[7,33,5,1.0,0.0,3.383],[14,44,12,1.0,0.0,3.382],[0,18,20,1.0,0.0,3.381],[4,33,3,1.0,0.0,3.378],[1,25,20,1.0,0.0,3.374],[39,54,30,1.0,0.0,3.367],[1,20,5,1.0,0.0,3.36],[5,45,5,1.0,0.0,3.342],[4,20,20,1.0,0.0,3.325],[21,49,20,1.0,0.0,3.32],[6,38,20,1.0,0.0,3.318],[25,52,5,1.0,0.0,3.317],[0,25,20,1.0,0.0,3.316],[16,37,10,1.0,0.0,3.292],[6,21,20,1.0,0.0,3.288],[4,26,20,1.0,0.0,3.282],[13,38,8,1.0,0.0,3.281],[41,56,20,1.0,0.0,3.268],[9,30,20,1.0,0.0,3.268],[4,29,4,1.0,0.0,3.246],[25,49,5,1.0,0.0,3.227],[14,43,12,1.0,0.0,3.223],[19,48,5,1.0,0.0,3.204],[8,19,25,1.0,0.0,3.194],[9,34,20,1.0,0.0,3.188],[3,28,5,1.0,0.0,3.184],[8,35,30,1.0,0.0,3.183],[3,26,30,1.0,0.0,3.183],[32,54,8,1.0,0.0,3.175],[20,44,5,1.0,0.0,3.17],[7,30,20,1.0,0.0,3.169],[6,24,20,1.0,0.0,3.167],[16,46,20,1.0,0.0,3.146],[14,32,20,1.0,0.0,3.129],[0,28,25,1.0,0.0,3.093],[9,29,20,1.0,0.0,3.088],[8,37,30,1.0,0.0,3.088],[2,22,20,1.0,0.0,3.087],[27,50,20,1.0,0.0,3.084],[14,35,6,1.0,0.0,3.082],[8,28,25,1.0,0.0,3.056],[2,19,20,1.0,0.0,3.055],[7,26,20,1.0,0.0,3.048],[8,34,20,1.0,0.0,3.037],[5,28,25,1.0,0.0,3.024],[14,45,8,1.0,0.0,3.018],[11,35,30,1.0,0.0,3.006],[32,45,8,1.0,0.0,3.002],[0,14,20,1.0,0.0,2.991],[6,30,20,1.0,0.0,2.988],[26,45,5,1.0,0.0,2.973],[18,45,20,1.0,0.0,2.966],[14,30,20,1.0,0.0,2.963],[0,21,20,1.0,0.0,2.933],[12,37,10,1.0,0.0,2.932],[7,27,20,1.0,0.0,2.931],[6,27,20,1.0,0.0,2.925],[24,49,20,1.0,0.0,2.914],[14,41,8,1.0,0.0,2.912],[24,47,20,1.0,0.0,2.908],[24,46,20,1.0,0.0,2.898],[31,52,7,1.0,0.0,2.886],[36,52,20,1.0,0.0,2.873],[6,26,20,1.0,0.0,2.855],[5,29,5,1.0,0.0,2.842],[28,45,5,1.0,0.0,2.837],[10,30,20,1.0,0.0,2.83],[32,47,8,1.0,0.0,2.825],[19,45,5,1.0,0.0,2.812],[17,46,20,1.0,0.0,2.803],[36,49,5,1.0,0.0,2.803],[7,19,25,1.0,0.0,2.793],[0,11,20,1.0,0.0,2.785],[20,47,5,1.0,0.0,2.769],[1,9,5,1.0,0.0,2.763],[47,52,5,1.0,0.0,2.753],[8,29,20,1.0,0.0,2.753],[4,19,20,1.0,0.0,2.735],[27,49,20,1.0,0.0,2.73],[21,48,20,1.0,0.0,2.718],[1,15,20,1.0,0.0,2.716],[1,19,25,1.0,0.0,2.715],[28,48,5,1.0,0.0,2.71],[20,42,20,1.0,0.0,2.647],[36,43,5,1.0,0.0,2.637],[6,34,20,1.0,0.0,2.612],[21,43,20,1.0,0.0,2.599],[25,43,9,1.0,0.0,2.591],[9,26,20,1.0,0.0,2.57],[0,15,20,1.0,0.0,2.562],[3,27,5,1.0,0.0,2.557],[16,35,6,1.0,0.0,2.553],[5,19,25,1.0,0.0,2.543],[1,10,5,1.0,0.0,2.532],[25,44,8,1.0,0.0,2.517],[6,19,25,1.0,0.0,2.508],[24,44,20,1.0,0.0,2.49],[5,10,5,1.0,0.0,2.454],[31,49,9,1.0,0.0,2.424],[4,15,20,1.0,0.0,2.415],[5,15,20,1.0,0.0,2.406],[16,30,6,1.0,0.0,2.345],[9,28,25,1.0,0.0,2.335],[2,9,20,1.0,0.0,2.321],[0,10,30,1.0,0.0,2.271],[6,17,20,1.0,0.0,2.263],[6,13,20,1.0,0.0,2.161],[23,30,6,1.0,0.0,2.143],[31,43,10,1.0,0.0,2.103],[1,7,5,1.0,0.0,2.05],[13,28,20,1.0,0.0,2.026],[12,27,20,1.0,0.0,1.988],[11,27,6,1.0,0.0,1.983],[16,32,6,1.0,0.0,1.958],[19,37,5,1.0,0.0,1.883],[23,37,10,1.0,0.0,1.822],[8,18,20,1.0,0.0,1.813],[0,12,30,0.983,0.033,2.841],[7,28,25,0.98,0.039,2.887],[12,28,25,0.98,0.039,2.273],[9,18,25,0.98,0.039,1.771],[17,47,20,0.975,0.049,3.44],[5,22,20,0.975,0.049,3.399],[6,18,20,0.975,0.049,3.253],[38,55,20,0.975,0.049,3.203],[13,41,20,0.975,0.049,3.184],[10,26,20,0.975,0.049,3.019],[10,18,20,0.975,0.049,2.787],[10,27,20,0.975,0.049,2.721],[8,27,20,0.975,0.049,2.587],[25,42,20,0.975,0.049,2.433],[24,43,20,0.975,0.049,2.413],[47,55,20,0.975,0.049,2.337],[21,45,20,0.975,0.049,2.304],[46,54,20,0.975,0.049,2.292],[13,32,20,0.975,0.049,2.147],[4,9,20,0.975,0.049,1.975],[0,8,30,0.967,0.065,2.436],[11,28,25,0.96,0.078,2.44],[18,50,20,0.95,0.098,3.467],[15,42,20,0.95,0.098,3.24],[24,48,20,0.95,0.098,3.191],[7,29,20,0.95,0.098,3.168],[4,22,20,0.95,0.098,2.95],[24,50,20,0.95,0.098,2.816],[13,27,20,0.95,0.098,2.814],[10,29,20,0.95,0.067,2.775],[3,15,20,0.95,0.098,2.708],[2,15,20,0.95,0.098,2.636],[29,42,20,0.95,0.098,2.347],[10,34,20,0.95,0.098,2.315],[6,10,20,0.95,0.067,2.116],[14,37,10,0.95,0.098,2.067],[31,44,10,0.95,0.098,2.027],[20,36,20,0.95,0.098,2.012],[16,23,10,0.95,0.098,1.903],[14,23,10,0.95,0.098,1.75],[0,7,30,0.95,0.072,1.714],[2,5,20,0.95,0.098,1.598],[10,28,25,0.94,0.065,2.603],[13,30,8,0.938,0.122,2.858],[47,54,8,0.938,0.122,2.283],[14,27,30,0.933,0.091,2.767],[37,45,30,0.933,0.091,2.383],[3,9,45,0.933,0.059,1.933],[15,33,7,0.929,0.14,2.202],[29,50,20,0.925,0.107,3.523],[32,50,20,0.925,0.08,2.799],[41,55,20,0.925,0.08,2.783],[51,56,20,0.925,0.107,2.762],[34,50,20,0.925,0.107,2.723],[17,34,20,0.925,0.107,2.568],[32,49,20,0.925,0.107,2.526],[15,26,20,0.925,0.107,2.089],[31,42,20,0.925,0.08,1.916],[20,31,20,0.925,0.107,1.91],[13,19,20,0.925,0.107,1.675],[14,21,20,0.925,0.08,1.111],[10,19,25,0.92,0.093,2.355],[11,19,25,0.92,0.093,2.2],[12,19,25,0.92,0.093,1.751],[40,54,30,0.917,0.095,2.776],[16,27,6,0.917,0.163,2.081],[32,46,39,0.91,0.079,1.919],[17,41,20,0.9,0.135,2.775],[41,52,5,0.9,0.196,2.588],[13,34,20,0.9,0.115,2.565],[14,19,20,0.9,0.135,2.528],[38,49,20,0.9,0.135,2.51],[19,33,20,0.9,0.135,2.45],[41,54,20,0.9,0.135,2.411],[55,56,20,0.9,0.115,2.196],[31,47,10,0.9,0.196,2.148],[9,19,25,0.9,0.098,2.146],[31,41,10,0.9,0.196,2.135],[15,29,10,0.9,0.196,2.087],[20,41,5,0.9,0.196,2.04],[22,29,10,0.9,0.196,2.007],[13,21,20,0.9,0.115,1.994],[14,28,20,0.9,0.09,1.987],[36,42,20,0.9,0.115,1.811],[20,34,15,0.9,0.105,1.728],[28,37,5,0.9,0.196,1.72],[36,44,5,0.9,0.196,1.68],[34,42,20,0.9,0.135,1.656],[25,34,10,0.9,0.196,1.485],[36,45,5,0.9,0.196,1.31],[7,18,20,0.9,0.09,1.251],[1,6,50,0.88,0.072,1.305],[34,54,8,0.875,0.245,3.125],[38,54,8,0.875,0.245,2.708],[29,43,20,0.875,0.14,2.386],[25,45,8,0.875,0.245,2.385],[38,50,20,0.875,0.14,1.964],[43,45,8,0.875,0.245,1.858],[6,12,20,0.875,0.097,1.721],[41,44,8,0.875,0.245,1.685],[6,11,20,0.875,0.121,1.471],[27,37,30,0.867,0.104,1.757],[6,9,25,0.86,0.12,1.715],[30,45,7,0.857,0.28,3.01],[22,45,7,0.857,0.28,2.648],[29,45,20,0.85,0.161,3.092],[34,49,20,0.85,0.161,2.534],[21,34,20,0.85,0.161,2.519],[6,7,20,0.85,0.144,1.227],[4,5,20,0.85,0.103,1.067],[23,34,6,0.833,0.207,1.81],[23,35,6,0.833,0.327,1.665],[6,14,20,0.825,0.147,2.116],[16,28,20,0.825,0.147,1.774],[15,19,20,0.825,0.163,1.276],[46,49,20,0.825,0.163,1.269],[0,9,30,0.817,0.099,1.24],[40,45,30,0.817,0.129,1.183],[17,38,20,0.8,0.165,1.65],[5,7,5,0.8,0.24,1.63],[33,45,5,0.8,0.392,1.611],[28,35,5,0.8,0.24,1.559],[28,33,20,0.8,0.165,1.497],[32,37,30,0.8,0.13,1.342],[9,15,20,0.8,0.165,1.301],[19,35,5,0.8,0.392,1.262],[47,50,20,0.8,0.149,1.168],[13,23,10,0.8,0.217,1.118],[24,38,20,0.8,0.165,1.113],[30,37,30,0.783,0.121,0.856],[46,55,20,0.775,0.181,1.873],[27,40,20,0.775,0.166,1.698],[22,42,20,0.775,0.181,1.568],[17,32,20,0.775,0.181,1.382],[22,26,20,0.775,0.181,1.209],[1,4,20,0.775,0.15,0.645],[27,30,30,0.767,0.139,0.769],[46,50,38,0.763,0.121,1.155],[29,49,20,0.75,0.195,2.291],[41,49,20,0.75,0.181,2.06],[41,45,20,0.75,0.195,1.53],[24,30,20,0.75,0.181,1.506],[14,29,20,0.75,0.167,1.432],[51,54,30,0.75,0.147,1.397],[24,41,20,0.75,0.167,1.337],[41,47,20,0.75,0.195,1.148],[31,45,10,0.75,0.263,1.103],[21,30,20,0.75,0.151,0.952],[27,35,30,0.75,0.147,0.902],[24,32,20,0.75,0.181,0.891],[19,26,20,0.75,0.181,0.87],[22,19,20,0.75,0.195,0.608],[31,36,10,0.75,0.219,0.602],[32,35,4,0.75,0.283,0.571],[38,45,30,0.733,0.147,1.644],[41,50,20,0.725,0.194,1.74],[13,29,20,0.725,0.194,1.569],[23,28,20,0.725,0.181,1.12],[27,28,20,0.725,0.181,0.686],[18,28,50,0.71,0.122,0.742],[29,30,39,0.705,0.133,0.429],[20,33,5,0.7,0.392,1.461],[41,46,20,0.7,0.206,1.255],[22,33,10,0.7,0.299,1.152],[41,42,20,0.7,0.193,1.05],[32,39,20,0.7,0.193,0.94],[20,29,20,0.7,0.18,0.897],[20,25,20,0.7,0.193,0.878],[42,49,20,0.7,0.18,0.867],[32,28,5,0.7,0.24,0.837],[20,26,20,0.7,0.18,0.698],[0,5,5,0.7,0.392,0.663],[34,33,5,0.7,0.392,0.607],[25,33,10,0.7,0.261,0.41],[0,3,45,0.678,0.121,0.533],[21,29,20,0.675,0.192,0.63],[34,37,30,0.667,0.158,0.991],[22,34,10,0.65,0.294,0.847],[21,28,20,0.65,0.202,0.719],[31,33,10,0.65,0.255,0.595],[17,30,20,0.65,0.202,0.587],[21,26,20,0.65,0.176,0.143],[1,3,45,0.644,0.106,0.492],[21,27,37,0.635,0.145,0.516],[23,27,30,0.633,0.162,0.577],[27,34,50,0.63,0.128,0.868],[16,19,20,0.625,0.2,0.585],[20,28,20,0.625,0.186,0.524],[17,27,20,0.625,0.186,0.485],[34,45,20,0.625,0.2,0.418],[25,26,20,0.625,0.212,0.413],[34,35,4,0.625,0.469,0.409],[6,8,60,0.625,0.098,0.397],[2,4,50,0.61,0.113,0.31],[44,52,5,0.6,0.48,1.396],[32,40,20,0.6,0.208,1.035],[31,34,10,0.6,0.285,0.857],[5,9,5,0.6,0.367,0.483],[1,5,5,0.6,0.196,0.464],[13,14,30,0.6,0.159,0.404],[7,9,25,0.58,0.167,0.078],[20,19,20,0.575,0.205,0.211],[22,43,7,0.571,0.396,0.545],[25,29,10,0.55,0.271,0.498],[8,10,20,0.55,0.173,0.28],[17,28,20,0.55,0.2,0.277],[1,0,20,0.55,0.2,0.216],[29,18,20,0.55,0.187,0.106],[24,27,20,0.55,0.212,0.056],[8,7,20,0.55,0.2,-0.042],[35,37,30,0.533,0.162,0.164],[2,0,60,0.533,0.111,0.112],[27,29,39,0.526,0.153,0.129],[32,38,20,0.525,0.219,0.627],[41,38,20,0.525,0.219,0.207],[46,44,20,0.525,0.194,0.099],[24,28,20,0.525,0.194,-0.028],[28,26,20,0.525,0.207,-0.223],[17,29,20,0.5,0.201,0.46],[24,34,20,0.5,0.213,0.344],[24,21,20,0.5,0.225,0.215],[49,50,20,0.5,0.213,-0.003],[34,30,20,0.5,0.201,-0.04],[39,35,4,0.5,0.566,-0.044],[4,0,20,0.5,0.201,-0.194],[31,29,10,0.5,0.327,-0.228],[18,19,20,0.5,0.201,-0.437],[17,21,20,0.475,0.194,0.35],[11,12,20,0.475,0.181,-0.009],[24,18,20,0.475,0.181,-0.038],[17,19,20,0.475,0.194,-0.043],[42,45,20,0.475,0.207,-0.123],[47,44,20,0.475,0.219,-0.343],[41,34,20,0.475,0.219,-0.843],[41,36,15,0.467,0.243,-0.93],[10,7,40,0.463,0.133,-0.21],[32,30,39,0.462,0.141,-0.387],[8,9,25,0.46,0.169,0.015],[10,9,25,0.46,0.169,-0.193],[24,29,20,0.45,0.212,0.389],[46,43,20,0.45,0.2,-0.05],[43,42,20,0.45,0.2,-0.075],[44,45,20,0.45,0.212,-0.098],[46,40,20,0.45,0.2,-0.114],[17,18,40,0.45,0.144,-0.193],[13,11,20,0.45,0.212,-0.279],[47,43,20,0.45,0.212,-0.338],[29,26,20,0.45,0.187,-0.6],[1,2,50,0.44,0.118,-0.148],[21,18,40,0.438,0.132,-0.363],[38,37,30,0.433,0.174,-0.53],[47,49,20,0.425,0.205,0.093],[21,19,20,0.425,0.192,-0.056],[32,34,40,0.425,0.151,-0.082],[44,43,20,0.425,0.192,-0.185],[2,3,40,0.425,0.138,-0.22],[47,42,20,0.425,0.192,-0.273],[44,42,20,0.425,0.192,-0.292],[29,28,20,0.425,0.205,-0.509],[50,45,20,0.425,0.217,-0.58],[32,29,20,0.4,0.196,-0.228],[6,3,5,0.4,0.367,-0.433],[6,5,5,0.4,0.367,-0.453],[39,37,10,0.4,0.32,-0.491],[31,25,20,0.4,0.208,-0.53],[40,37,10,0.4,0.285,-0.584],[14,10,15,0.4,0.218,-0.638],[55,54,20,0.4,0.208,-0.953],[40,28,5,0.4,0.48,-0.973],[29,33,5,0.4,0.48,-1.281],[25,22,20,0.375,0.212,-0.159],[30,35,4,0.375,0.469,-0.199],[30,28,20,0.375,0.212,-0.725],[12,10,15,0.367,0.224,-0.767],[20,22,20,0.35,0.202,-0.116],[20,21,20,0.35,0.202,-0.496],[46,45,20,0.35,0.202,-0.562],[22,15,20,0.35,0.189,-1.577],[12,7,15,0.333,0.228,-0.709],[11,7,15,0.333,0.207,-0.891],[13,10,15,0.333,0.207,-0.941],[47,38,30,0.333,0.158,-1.04],[34,26,15,0.333,0.247,-1.308],[24,17,20,0.325,0.178,-0.722],[13,12,20,0.325,0.192,-0.726],[53,52,20,0.325,0.205,-0.808],[47,46,20,0.325,0.205,-0.809],[38,34,20,0.325,0.205,-0.856],[12,8,60,0.308,0.099,-0.608],[32,41,20,0.3,0.193,-0.478],[25,19,20,0.3,0.18,-0.602],[34,28,5,0.3,0.392,-0.631],[30,19,20,0.3,0.165,-0.73],[32,27,40,0.3,0.13,-0.792],[11,10,15,0.3,0.23,-0.826],[51,46,20,0.3,0.206,-1.017],[29,19,20,0.3,0.18,-1.257],[38,30,20,0.3,0.206,-1.533],[51,40,20,0.3,0.18,-1.596],[41,25,10,0.3,0.261,-1.711],[11,8,40,0.287,0.126,-0.827],[44,22,7,0.286,0.361,-1.819],[39,40,20,0.275,0.181,-0.893],[27,19,20,0.275,0.194,-1.013],[39,34,20,0.275,0.194,-1.057],[54,49,20,0.275,0.181,-1.14],[36,29,20,0.275,0.181,-1.155],[34,29,20,0.275,0.194,-1.42],[41,21,20,0.275,0.181,-1.44],[14,7,15,0.267,0.211,-0.785],[23,19,20,0.25,0.181,-0.893],[16,14,10,0.25,0.163,-0.906],[11,9,20,0.25,0.181,-0.99],[47,45,20,0.25,0.151,-1.078],[39,27,20,0.25,0.181,-1.202],[31,22,20,0.25,0.195,-1.245],[41,27,20,0.25,0.167,-1.324],[46,38,20,0.25,0.181,-1.546],[16,12,6,0.25,0.335,-1.579],[52,42,20,0.25,0.181,-1.685],[55,50,20,0.25,0.181,-2.327],[13,8,60,0.233,0.082,-1.003],[14,11,30,0.233,0.139,-1.089],[51,45,30,0.233,0.154,-1.314],[31,26,20,0.225,0.166,-1.218],[53,49,20,0.225,0.166,-1.28],[24,19,20,0.225,0.181,-1.282],[30,18,20,0.225,0.166,-1.358],[25,15,20,0.225,0.181,-1.525],[55,45,20,0.225,0.181,-2.04],[55,49,20,0.225,0.181,-2.241],[5,3,45,0.222,0.106,-0.914],[14,12,30,0.217,0.112,-1.159],[16,8,40,0.212,0.116,-1.551],[12,9,20,0.2,0.131,-0.907],[41,28,5,0.2,0.392,-0.916],[32,21,20,0.2,0.165,-1.008],[36,25,10,0.2,0.261,-1.082],[27,18,20,0.2,0.149,-1.127],[13,9,20,0.2,0.165,-1.254],[40,34,20,0.2,0.18,-1.322],[36,21,20,0.2,0.165,-1.367],[36,22,10,0.2,0.261,-1.698],[38,27,30,0.2,0.138,-1.705],[43,33,5,0.2,0.392,-1.749],[36,33,5,0.2,0.392,-1.758],[43,28,5,0.2,0.392,-1.993],[47,33,5,0.2,0.392,-2.001],[52,49,5,0.2,0.392,-2.077],[49,19,5,0.2,0.392,-3.467],[52,22,50,0.18,0.108,-2.77],[4,3,20,0.175,0.147,-0.907],[28,19,20,0.175,0.129,-1.021],[16,13,20,0.175,0.129,-1.344],[41,29,20,0.175,0.147,-1.786],[44,29,20,0.175,0.163,-1.903],[22,9,20,0.175,0.129,-1.933],[6,0,30,0.167,0.118,-0.962],[32,23,6,0.167,0.207,-1.903],[47,34,30,0.167,0.127,-1.935],[47,22,6,0.167,0.327,-2.294],[14,8,40,0.163,0.102,-1.321],[46,37,20,0.15,0.144,-1.699],[20,15,20,0.15,0.161,-1.806],[17,14,20,0.15,0.161,-1.977],[51,27,20,0.15,0.161,-3.104],[46,36,50,0.14,0.084,-1.535],[56,52,50,0.14,0.093,-1.979],[40,35,4,0.125,0.245,-1.135],[42,33,20,0.125,0.121,-1.586],[14,9,20,0.125,0.14,-1.602],[46,34,20,0.125,0.14,-1.704],[38,21,20,0.125,0.14,-1.875],[51,32,20,0.125,0.14,-2.414],[17,10,40,0.113,0.089,-1.881],[33,26,5,0.1,0.196,-1.131],[36,28,5,0.1,0.196,-1.202],[41,33,5,0.1,0.196,-1.653],[46,39,20,0.1,0.135,-1.659],[54,50,20,0.1,0.115,-1.706],[36,34,5,0.1,0.196,-1.825],[46,29,20,0.1,0.135,-1.919],[36,26,20,0.1,0.135,-1.95],[16,11,10,0.1,0.196,-2.093],[56,54,20,0.1,0.115,-2.193],[46,35,20,0.1,0.115,-2.195],[53,50,20,0.1,0.115,-2.208],[34,18,20,0.1,0.135,-2.222],[32,18,20,0.1,0.135,-2.234],[43,26,5,0.1,0.196,-2.39],[52,43,5,0.1,0.196,-2.417],[43,19,5,0.1,0.196,-2.462],[41,22,10,0.1,0.196,-2.497],[53,29,20,0.1,0.115,-2.55],[24,10,20,0.1,0.115,-2.56],[21,10,20,0.1,0.135,-2.56],[21,9,25,0.1,0.113,-2.608],[52,29,20,0.1,0.135,-2.982],[51,34,20,0.1,0.135,-2.988],[51,37,10,0.1,0.196,-3.191],[55,28,5,0.1,0.196,-3.8],[47,25,6,0.083,0.163,-2.083],[32,20,50,0.08,0.065,-1.856],[31,19,20,0.075,0.08,-1.783],[49,45,20,0.075,0.107,-1.938],[20,7,20,0.075,0.107,-2.132],[46,21,20,0.075,0.107,-2.337],[53,42,20,0.075,0.08,-2.423],[56,40,20,0.075,0.107,-4.395],[36,15,7,0.071,0.14,-2.44],[13,7,15,0.067,0.131,-1.573],[47,37,30,0.067,0.062,-1.849],[17,9,25,0.06,0.086,-2.222],[10,3,50,0.05,0.042,-1.62],[7,3,20,0.05,0.067,-1.689],[13,0,20,0.05,0.067,-2.077],[17,8,20,0.05,0.067,-2.467],[31,15,20,0.05,0.098,-2.545],[46,30,20,0.05,0.098,-2.615],[24,9,20,0.05,0.098,-2.791],[34,15,50,0.05,0.058,-2.793],[47,21,20,0.05,0.098,-2.939],[47,29,20,0.05,0.098,-3.408],[32,9,20,0.05,0.098,-3.52],[56,49,20,0.05,0.098,-4.202],[55,34,20,0.05,0.098,-4.218],[56,34,20,0.05,0.098,-4.653],[56,50,39,0.026,0.05,-3.083],[24,14,20,0.025,0.049,-2.202],[20,9,20,0.025,0.049,-2.258],[21,7,20,0.025,0.049,-2.346],[25,9,20,0.025,0.049,-2.581],[21,8,20,0.025,0.049,-2.753],[16,0,20,0.025,0.049,-3.252],[32,7,20,0.025,0.049,-3.294],[20,3,30,0.017,0.033,-3.063],[11,3,5,0.0,0.0,-1.56],[47,36,5,0.0,0.0,-1.653],[12,3,5,0.0,0.0,-1.767],[39,28,5,0.0,0.0,-1.992],[51,47,2,0.0,0.0,-2.0],[36,19,5,0.0,0.0,-2.0],[23,11,10,0.0,0.0,-2.072],[38,35,4,0.0,0.0,-2.082],[41,18,20,0.0,0.0,-2.129],[23,12,10,0.0,0.0,-2.19],[38,28,5,0.0,0.0,-2.2],[39,19,5,0.0,0.0,-2.24],[17,7,20,0.0,0.0,-2.281],[46,28,5,0.0,0.0,-2.307],[41,26,5,0.0,0.0,-2.322],[8,3,5,0.0,0.0,-2.35],[46,23,20,0.0,0.0,-2.374],[16,3,5,0.0,0.0,-2.378],[17,3,5,0.0,0.0,-2.507],[47,19,5,0.0,0.0,-2.51],[23,8,10,0.0,0.0,-2.546],[42,26,20,0.0,0.0,-2.588],[32,19,5,0.0,0.0,-2.59],[21,5,50,0.0,0.0,-2.627],[46,18,20,0.0,0.0,-2.648],[46,27,20,0.0,0.0,-2.662],[41,15,5,0.0,0.0,-2.713],[44,15,4,0.0,0.0,-2.788],[49,33,5,0.0,0.0,-2.788],[42,19,20,0.0,0.0,-2.823],[24,7,20,0.0,0.0,-2.845],[44,33,5,0.0,0.0,-2.867],[48,33,5,0.0,0.0,-2.877],[44,21,20,0.0,0.0,-2.889],[50,33,5,0.0,0.0,-2.897],[43,18,20,0.0,0.0,-2.902],[14,3,5,0.0,0.0,-2.91],[53,33,5,0.0,0.0,-2.946],[34,19,5,0.0,0.0,-2.953],[25,5,20,0.0,0.0,-2.956],[40,30,4,0.0,0.0,-2.958],[32,12,20,0.0,0.0,-2.965],[47,27,30,0.0,0.0,-2.973],[21,3,5,0.0,0.0,-2.987],[44,19,5,0.0,0.0,-3.01],[41,19,5,0.0,0.0,-3.027],[52,34,5,0.0,0.0,-3.056],[32,10,20,0.0,0.0,-3.057],[52,19,5,0.0,0.0,-3.058],[54,37,30,0.0,0.0,-3.077],[13,3,5,0.0,0.0,-3.08],[27,9,20,0.0,0.0,-3.097],[36,9,20,0.0,0.0,-3.112],[32,8,20,0.0,0.0,-3.139],[46,19,5,0.0,0.0,-3.14],[24,8,20,0.0,0.0,-3.142],[46,3,5,0.0,0.0,-3.197],[44,26,5,0.0,0.0,-3.2],[20,5,5,0.0,0.0,-3.202],[20,10,20,0.0,0.0,-3.211],[50,26,50,0.0,0.0,-3.216],[56,43,20,0.0,0.0,-3.22],[47,28,5,0.0,0.0,-3.223],[31,9,20,0.0,0.0,-3.245],[53,22,4,0.0,0.0,-3.263],[51,28,5,0.0,0.0,-3.267],[54,28,5,0.0,0.0,-3.271],[36,7,20,0.0,0.0,-3.277],[54,45,8,0.0,0.0,-3.283],[53,28,5,0.0,0.0,-3.284],[46,10,20,0.0,0.0,-3.332],[54,30,5,0.0,0.0,-3.348],[39,30,4,0.0,0.0,-3.358],[36,5,5,0.0,0.0,-3.36],[41,10,20,0.0,0.0,-3.362],[47,15,3,0.0,0.0,-3.378],[36,10,20,0.0,0.0,-3.378],[44,18,20,0.0,0.0,-3.387],[17,0,30,0.0,0.0,-3.404],[44,28,5,0.0,0.0,-3.41],[52,33,5,0.0,0.0,-3.423],[53,18,20,0.0,0.0,-3.441],[47,30,7,0.0,0.0,-3.455],[36,3,5,0.0,0.0,-3.469],[47,26,5,0.0,0.0,-3.47],[38,19,5,0.0,0.0,-3.49],[44,8,20,0.0,0.0,-3.505],[44,10,20,0.0,0.0,-3.513],[49,26,5,0.0,0.0,-3.525],[52,26,20,0.0,0.0,-3.544],[47,18,20,0.0,0.0,-3.551],[25,3,20,0.0,0.0,-3.558],[38,3,5,0.0,0.0,-3.567],[56,48,20,0.0,0.0,-3.571],[52,15,3,0.0,0.0,-3.639],[52,28,5,0.0,0.0,-3.643],[46,9,20,0.0,0.0,-3.683],[46,12,20,0.0,0.0,-3.696],[47,10,20,0.0,0.0,-3.773],[23,3,5,0.0,0.0,-3.802],[49,18,20,0.0,0.0,-3.81],[24,3,5,0.0,0.0,-3.82],[31,5,20,0.0,0.0,-3.875],[51,19,5,0.0,0.0,-3.903],[47,8,20,0.0,0.0,-3.939],[31,3,20,0.0,0.0,-3.943],[38,5,5,0.0,0.0,-3.946],[40,19,5,0.0,0.0,-3.95],[53,26,5,0.0,0.0,-3.968],[56,45,20,0.0,0.0,-3.974],[46,8,20,0.0,0.0,-3.978],[24,0,20,0.0,0.0,-3.981],[41,5,5,0.0,0.0,-4.058],[41,7,20,0.0,0.0,-4.063],[49,28,5,0.0,0.0,-4.103],[41,8,20,0.0,0.0,-4.116],[46,11,20,0.0,0.0,-4.163],[47,9,15,0.0,0.0,-4.178],[44,7,20,0.0,0.0,-4.216],[56,29,20,0.0,0.0,-4.226],[54,19,5,0.0,0.0,-4.246],[38,8,8,0.0,0.0,-4.261],[47,3,20,0.0,0.0,-4.265],[53,19,5,0.0,0.0,-4.357],[41,9,20,0.0,0.0,-4.376],[44,3,20,0.0,0.0,-4.382],[44,9,20,0.0,0.0,-4.386],[44,5,5,0.0,0.0,-4.417],[46,7,20,0.0,0.0,-4.431],[51,3,5,0.0,0.0,-4.477],[56,37,20,0.0,0.0,-4.477],[47,5,5,0.0,0.0,-4.48],[41,3,20,0.0,0.0,-4.499],[56,28,5,0.0,0.0,-4.507],[51,8,20,0.0,0.0,-4.539],[47,7,20,0.0,0.0,-4.629],[55,27,20,0.0,0.0,-4.658],[55,19,5,0.0,0.0,-4.66],[56,35,20,0.0,0.0,-4.694],[32,3,5,0.0,0.0,-4.817],[55,29,20,0.0,0.0,-4.828],[53,15,3,0.0,0.0,-4.9],[56,27,20,0.0,0.0,-4.977],[53,9,15,0.0,0.0,-5.066],[56,39,20,0.0,0.0,-5.14],[56,30,20,0.0,0.0,-5.529],[56,19,5,0.0,0.0,-5.6],[56,9,15,0.0,0.0,-5.798],[56,18,20,0.0,0.0,-6.06],[52,9,20,0.0,0.0,-6.159]]}},"debate":{"title":"Debate","metric":{"name":"Bradley-Terry rating","scale":"Relative within-pool rating centred near 1500; higher is better","interval":"95% robust (sandwich) confidence interval","count":"Complete side-swapped matchups (two debates, sides reversed)","availability":"Percent of scheduled side-swapped matchups completed"},"description":"Models debate the same motion twice with PRO and CON sides swapped. A three-model judge panel decides each debate's winner and margin; ratings use complete side-swapped matchups.","sourceUrl":"https://github.com/lechmazur/debate","readmeUrl":"https://github.com/lechmazur/debate/blob/72d2063e321c30a34687f6ce325773b60a878546/README.md","dataUrl":"https://github.com/lechmazur/debate/tree/72d2063e321c30a34687f6ce325773b60a878546/judgments","snapshotDate":"2026-09-24","scope":"judge_judge_blend_20260923_finala__debate_all_templates","sourceCommit":"72d2063e321c30a34687f6ce325773b60a878546","sourceCommitDate":"2026-09-25T16:16:20-04:00","sourceFiles":{"README.md":"ab6388ebaca53637","reports/debate_leaderboard__judge_judge_blend_20260923_finala__debate_all_templates.md":"3c2f2d555a34b124","debate_model_ratings__judge_judge_blend_20260923_finala__debate_all_templates.csv":"ee688ba50eedb9f9","debate_pair_stats__judge_judge_blend_20260923_finala__debate_all_templates.csv":"1e70618073ceedbc"},"provenance":{"headline":"Rank, BT, matchups, availability, topics, and opponents are the published values in README.md and reports/debate_leaderboard__judge_judge_blend_20260923_finala__debate_all_templates.md.","intervals":"low/high are bt_ci95_low_norm and bt_ci95_high_norm from debate_model_ratings__judge_judge_blend_20260923_finala__debate_all_templates.csv, the ratings table behind the published chart images/debate_bt_ratings__judge_judge_blend_20260923_finala__debate_all_templates.png.","pairs":"Pair margins (mean_signed_margin_a_norm) and matchup counts (topic_pairs) are from debate_pair_stats__judge_judge_blend_20260923_finala__debate_all_templates.csv, the table behind the published heatmap images/debate_pair_margin_heatmap__judge_judge_blend_20260923_finala__debate_all_templates.png.","verification":"Both tables belong to the exact published scope. The leaderboard report generated with them is byte-identical to the published report; every exported BT, matchup, availability, topic, and opponent value matches it, and pair counts sum to the published 3,672 and 3,424 matchup totals."},"totals":{"ratedModels":59,"publicModels":56,"matchups":3672,"debates":7344,"judgeDecisions":22592,"topics":683,"publicMatchups":3424},"notes":["Intervals and head-to-head margins come from the data behind the published rating chart and heatmap; the provenance notes name the exact tables.","Pairs with only one or two matchups are directional evidence, not stable pairwise estimates."],"models":[{"id":"claude-fable-5-1-high","name":"Claude Fable 5.1 (high)","rank":1,"score":1737.6,"low":1726.4,"high":1748.7,"count":177,"topics":160,"opponents":26,"availability":95.7},{"id":"claude-fable-5-high","name":"Claude Fable 5 (high)","rank":2,"score":1726.5,"low":1716.2,"high":1736.8,"count":205,"topics":187,"opponents":35,"availability":93.2},{"id":"claude-opus-5-high","name":"Claude Opus 5 (high)","rank":3,"score":1724.2,"low":1712.4,"high":1735.9,"count":207,"topics":184,"opponents":33,"availability":98.6},{"id":"claude-opus-5-5-high","name":"Claude Opus 5.5 (high)","rank":4,"score":1701.0,"low":1687.6,"high":1714.3,"count":97,"topics":86,"opponents":13,"availability":97.0},{"id":"kimi-k3","name":"Kimi K3","rank":5,"score":1697.7,"low":1687.1,"high":1708.2,"count":200,"topics":177,"opponents":34,"availability":98.5},{"id":"claude-opus-4-7-adaptive","name":"Claude Opus 4.7 (high)","rank":6,"score":1648.5,"low":1637.2,"high":1659.7,"count":120,"topics":118,"opponents":32,"availability":97.6},{"id":"gpt-5.6-high","name":"GPT-5.6 Sol (high)","rank":7,"score":1645.1,"low":1635.1,"high":1655.2,"count":242,"topics":215,"opponents":36,"availability":98.4},{"id":"glm-5-3-high","name":"GLM-5.3 (high)","rank":8,"score":1639.0,"low":1626.3,"high":1651.8,"count":128,"topics":123,"opponents":24,"availability":98.5},{"id":"muse-spark-1.1-high","name":"Muse Spark 1.1 (high)","rank":9,"score":1637.5,"low":1627.1,"high":1647.8,"count":189,"topics":174,"opponents":30,"availability":98.4},{"id":"claude-opus-4-8-adaptive","name":"Claude Opus 4.8 (high)","rank":10,"score":1630.9,"low":1620.0,"high":1641.9,"count":165,"topics":139,"opponents":30,"availability":96.5},{"id":"grok-4.7-high","name":"Grok 4.7 (high)","rank":11,"score":1619.8,"low":1607.5,"high":1632.0,"count":99,"topics":94,"opponents":15,"availability":99.0},{"id":"mimo-v2.6-pro-thinking","name":"Xiaomi MiMo V2.6 Pro (thinking)","rank":12,"score":1609.2,"low":1594.9,"high":1623.5,"count":92,"topics":82,"opponents":17,"availability":92.0},{"id":"gpt-6-astra-high","name":"GPT-6 Astra (high)","rank":13,"score":1605.6,"low":1592.6,"high":1618.7,"count":152,"topics":150,"opponents":21,"availability":99.3},{"id":"grok-4.6-high","name":"Grok 4.6 (high)","rank":14,"score":1604.1,"low":1593.5,"high":1614.7,"count":197,"topics":178,"opponents":27,"availability":99.0},{"id":"muse-spark-1.3-high","name":"Muse Spark 1.3 (high)","rank":15,"score":1592.6,"low":1582.3,"high":1602.8,"count":179,"topics":173,"opponents":25,"availability":99.4},{"id":"claude-sonnet-5-high","name":"Claude Sonnet 5 (high)","rank":16,"score":1584.9,"low":1574.4,"high":1595.3,"count":217,"topics":194,"opponents":37,"availability":97.7},{"id":"deepseek-v4.1-flash-high","name":"DeepSeek V4.1 Flash (high)","rank":17,"score":1582.3,"low":1569.1,"high":1595.4,"count":100,"topics":97,"opponents":15,"availability":100.0},{"id":"hy4-preview-high","name":"Tencent Hy4 Preview (high)","rank":18,"score":1578.9,"low":1568.0,"high":1589.7,"count":194,"topics":173,"opponents":27,"availability":99.0},{"id":"deepseek-v4-pro-0813-high","name":"DeepSeek V4 Pro 0813 (high)","rank":19,"score":1572.1,"low":1560.0,"high":1584.1,"count":174,"topics":161,"opponents":27,"availability":100.0},{"id":"glm-5-2","name":"GLM-5.2 (max)","rank":20,"score":1563.1,"low":1551.8,"high":1574.4,"count":182,"topics":160,"opponents":33,"availability":98.4},{"id":"claude-sonnet-4-6-adaptive","name":"Claude Sonnet 4.6 (high)","rank":21,"score":1561.0,"low":1550.3,"high":1571.8,"count":139,"topics":134,"opponents":31,"availability":93.4},{"id":"qwen3.8-max","name":"Qwen 3.8 Max","rank":22,"score":1552.5,"low":1540.5,"high":1564.4,"count":163,"topics":154,"opponents":26,"availability":97.6},{"id":"gpt-5.4-high","name":"GPT-5.4 (high)","rank":23,"score":1547.6,"low":1535.8,"high":1559.4,"count":131,"topics":131,"opponents":30,"availability":97.1},{"id":"claude-sonnet-4-6-0K","name":"Claude Sonnet 4.6 (no reasoning)","rank":24,"score":1542.4,"low":1530.3,"high":1554.4,"count":85,"topics":85,"opponents":18,"availability":94.6},{"id":"gpt-5.5-high","name":"GPT-5.5 (high)","rank":25,"score":1527.5,"low":1516.8,"high":1538.2,"count":126,"topics":114,"opponents":27,"availability":100.0},{"id":"glm-5.1","name":"GLM-5.1","rank":26,"score":1518.7,"low":1505.0,"high":1532.3,"count":99,"topics":97,"opponents":22,"availability":97.1},{"id":"gemini-3.8-flash-high","name":"Gemini 3.8 Flash (high)","rank":27,"score":1514.2,"low":1501.2,"high":1527.2,"count":136,"topics":134,"opponents":26,"availability":99.3},{"id":"kimi-k2.6","name":"Kimi K2.6","rank":28,"score":1511.0,"low":1499.4,"high":1522.7,"count":131,"topics":122,"opponents":29,"availability":97.8},{"id":"minimax-m3","name":"MiniMax-M3","rank":29,"score":1502.2,"low":1490.4,"high":1513.9,"count":156,"topics":143,"opponents":32,"availability":97.5},{"id":"gpt-5.4-none","name":"GPT-5.4 (no reasoning)","rank":30,"score":1495.1,"low":1482.5,"high":1507.8,"count":95,"topics":95,"opponents":21,"availability":96.0},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","rank":31,"score":1491.0,"low":1481.4,"high":1500.6,"count":215,"topics":191,"opponents":51,"availability":96.4},{"id":"grok-4.5-high","name":"Grok 4.5 (high)","rank":32,"score":1490.2,"low":1474.4,"high":1505.9,"count":122,"topics":120,"opponents":26,"availability":100.0},{"id":"mimo-v2.5-pro","name":"Xiaomi MiMo V2.5 Pro","rank":33,"score":1483.7,"low":1473.2,"high":1494.1,"count":187,"topics":175,"opponents":41,"availability":95.4},{"id":"qwen3.6-max-preview","name":"Qwen 3.6 Max Preview","rank":34,"score":1474.6,"low":1461.8,"high":1487.4,"count":84,"topics":80,"opponents":20,"availability":100.0},{"id":"gemini-3.7-flash-high","name":"Gemini 3.7 Flash (high)","rank":35,"score":1455.2,"low":1441.4,"high":1469.0,"count":117,"topics":114,"opponents":18,"availability":99.2},{"id":"kimi-k2.5","name":"Kimi K2.5 Thinking","rank":36,"score":1453.8,"low":1436.2,"high":1471.3,"count":73,"topics":70,"opponents":26,"availability":90.2},{"id":"seed-2.0-pro","name":"ByteDance Seed2.0 Pro","rank":37,"score":1453.7,"low":1443.5,"high":1463.9,"count":176,"topics":163,"opponents":47,"availability":98.3},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro Preview","rank":38,"score":1447.7,"low":1434.4,"high":1461.0,"count":128,"topics":121,"opponents":34,"availability":100.0},{"id":"qwen3.7-max","name":"Qwen 3.7 Max","rank":39,"score":1433.8,"low":1423.2,"high":1444.4,"count":156,"topics":145,"opponents":30,"availability":98.2},{"id":"minimax-m2.7","name":"MiniMax-M2.7","rank":40,"score":1433.5,"low":1419.0,"high":1447.9,"count":89,"topics":87,"opponents":24,"availability":93.8},{"id":"grok-4.20-beta-0309-reasoning","name":"Grok 4.20 0309 (Reasoning)","rank":41,"score":1411.8,"low":1395.0,"high":1428.6,"count":49,"topics":49,"opponents":15,"availability":96.3},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","rank":42,"score":1406.9,"low":1395.0,"high":1418.8,"count":129,"topics":125,"opponents":31,"availability":99.2},{"id":"grok-4.20-beta-0309-non-reasoning","name":"Grok 4.20 0309 (Non-Reasoning)","rank":43,"score":1403.9,"low":1383.3,"high":1424.5,"count":36,"topics":36,"opponents":12,"availability":92.5},{"id":"mimo-v2-pro","name":"Xiaomi MiMo V2 Pro","rank":44,"score":1392.2,"low":1369.5,"high":1414.9,"count":30,"topics":30,"opponents":14,"availability":61.5},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","rank":45,"score":1389.7,"low":1379.1,"high":1400.3,"count":91,"topics":88,"opponents":30,"availability":96.0},{"id":"hy3-preview-high","name":"Tencent Hy3 Preview (high)","rank":46,"score":1385.7,"low":1370.7,"high":1400.7,"count":122,"topics":116,"opponents":31,"availability":98.4},{"id":"ernie-5.1","name":"Baidu Ernie 5.1","rank":47,"score":1383.3,"low":1372.1,"high":1394.5,"count":168,"topics":155,"opponents":37,"availability":100.0},{"id":"step-3.7-flash-high","name":"Step 3.7 Flash (high)","rank":48,"score":1381.8,"low":1370.0,"high":1393.6,"count":160,"topics":154,"opponents":36,"availability":97.6},{"id":"grok-4.3","name":"Grok 4.3","rank":49,"score":1370.3,"low":1356.1,"high":1384.5,"count":88,"topics":85,"opponents":25,"availability":98.9},{"id":"deepseek-v32-exp","name":"DeepSeek V3.2","rank":50,"score":1362.4,"low":1340.2,"high":1384.6,"count":41,"topics":41,"opponents":13,"availability":93.2},{"id":"mistral-medium-3.5-high","name":"Mistral Medium 3.5 (high)","rank":51,"score":1343.9,"low":1330.8,"high":1357.0,"count":117,"topics":109,"opponents":36,"availability":99.2},{"id":"gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash-Lite Preview","rank":52,"score":1330.0,"low":1307.7,"high":1352.3,"count":31,"topics":31,"opponents":10,"availability":91.7},{"id":"gpt-oss-120b","name":"GPT-OSS-120B","rank":53,"score":1270.4,"low":1242.4,"high":1298.4,"count":31,"topics":31,"opponents":8,"availability":100.0},{"id":"ernie-5","name":"Baidu Ernie 5.0","rank":54,"score":1246.8,"low":1222.9,"high":1270.8,"count":16,"topics":16,"opponents":6,"availability":100.0},{"id":"mistral-large-2512","name":"Mistral Large 3","rank":55,"score":1219.2,"low":1177.7,"high":1260.7,"count":22,"topics":22,"opponents":7,"availability":89.3},{"id":"llama4-maverick","name":"Llama 4 Maverick","rank":56,"score":1034.5,"low":1000.8,"high":1068.2,"count":29,"topics":29,"opponents":8,"availability":96.9}],"pairs":{"kind":"observed","fields":["a","b","matchups","aMeanSignedMargin"],"description":"Mean normalized signed judge margin for a over b; a and b index models[].","rows":[[0,1,17,-0.209],[0,3,15,0.122],[0,2,15,0.377],[0,15,4,1.639],[0,18,5,0.929],[0,16,3,1.837],[0,46,2,2.233],[0,30,5,1.518],[0,26,6,1.464],[0,19,1,1.818],[0,7,7,1.212],[0,6,12,0.925],[0,12,8,1.19],[0,13,11,1.09],[0,10,5,1.055],[0,17,8,1.431],[0,4,13,0.66],[0,32,4,1.668],[0,11,3,1.383],[0,28,5,1.93],[0,50,2,2.348],[0,8,12,1.229],[0,14,6,1.118],[0,21,4,1.569],[0,36,2,2.256],[0,47,2,2.073],[1,5,5,1.072],[1,9,5,0.627],[1,2,10,0.578],[1,15,5,1.446],[1,37,5,1.767],[1,18,10,1.261],[1,46,5,2.254],[1,30,5,1.543],[1,41,5,2.134],[1,34,10,1.885],[1,19,5,1.48],[1,25,5,1.555],[1,22,5,1.608],[1,24,5,1.321],[1,6,4,0.62],[1,48,5,2.099],[1,31,5,2.064],[1,13,10,0.975],[1,45,5,2.207],[1,17,3,1.629],[1,27,5,1.803],[1,4,5,0.602],[1,32,5,1.705],[1,39,4,1.821],[1,28,5,1.676],[1,50,5,2.202],[1,8,4,1.329],[1,44,5,2.069],[1,33,5,1.752],[1,38,4,2.045],[1,21,10,1.251],[1,36,5,1.932],[1,47,5,2.242],[5,9,5,0.308],[5,23,4,1.216],[5,20,4,0.74],[5,15,5,0.696],[5,49,4,1.785],[5,37,3,1.059],[5,46,5,2.019],[5,30,4,1.327],[5,41,4,1.82],[5,25,3,0.603],[5,22,4,0.936],[5,29,4,1.335],[5,24,3,1.239],[5,6,5,0.32],[5,40,4,1.607],[5,48,3,2.002],[5,45,2,1.696],[5,35,2,1.9],[5,27,3,1.443],[5,43,3,1.753],[5,32,3,1.672],[5,39,4,1.754],[5,50,2,2.043],[5,8,4,0.187],[5,44,4,1.858],[5,33,3,1.375],[5,38,5,1.615],[5,36,4,1.723],[5,47,4,2.074],[9,2,10,-1.026],[9,20,4,0.946],[9,15,5,0.175],[9,37,6,1.434],[9,46,5,2.051],[9,30,6,1.274],[9,41,5,1.908],[9,19,5,0.766],[9,25,6,1.111],[9,22,5,1.124],[9,24,6,1.122],[9,6,5,-0.365],[9,48,6,1.616],[9,31,5,1.346],[9,45,6,1.836],[9,27,6,0.696],[9,4,5,-0.718],[9,32,6,1.13],[9,39,5,1.771],[9,28,5,1.411],[9,50,6,2.048],[9,8,5,0.007],[9,44,5,1.809],[9,33,6,1.057],[9,38,5,1.581],[9,36,6,1.554],[9,47,5,1.7],[3,2,19,-0.293],[3,18,1,1.225],[3,16,5,1.156],[3,26,1,1.558],[3,7,11,0.7],[3,6,11,0.274],[3,13,9,0.826],[3,10,5,0.71],[3,17,2,1.345],[3,4,12,0.091],[3,11,4,0.839],[3,14,2,1.249],[2,15,8,1.508],[2,37,2,1.956],[2,18,10,1.259],[2,16,3,1.298],[2,46,2,2.261],[2,30,4,1.942],[2,41,2,2.207],[2,34,10,1.776],[2,26,4,1.465],[2,19,8,1.35],[2,7,5,0.693],[2,6,10,1.186],[2,12,6,1.14],[2,31,4,1.342],[2,13,10,0.958],[2,10,4,0.881],[2,45,2,1.985],[2,17,3,1.308],[2,4,10,0.415],[2,32,4,1.912],[2,11,3,1.334],[2,28,4,1.797],[2,50,2,2.515],[2,8,10,0.683],[2,14,4,1.213],[2,38,2,2.06],[2,21,12,1.297],[2,36,3,2.231],[2,47,2,2.649],[23,20,10,0.027],[23,49,4,1.414],[23,53,4,1.94],[23,51,4,1.812],[23,30,6,0.594],[23,22,8,0.062],[23,29,6,0.63],[23,42,4,1.024],[23,40,2,0.729],[23,35,5,1.34],[23,43,4,1.162],[23,39,2,0.426],[23,44,4,1.499],[23,36,4,0.773],[20,15,5,-0.491],[20,49,2,1.809],[20,37,4,0.998],[20,53,2,2.017],[20,46,4,1.411],[20,51,2,1.746],[20,30,8,0.536],[20,41,4,1.437],[20,25,4,0.58],[20,22,10,0.34],[20,29,8,0.876],[20,24,4,-0.062],[20,42,2,1.121],[20,40,2,1.047],[20,48,4,1.196],[20,45,4,1.656],[20,35,4,0.931],[20,27,4,1.095],[20,43,2,1.189],[20,32,4,0.76],[20,39,2,1.45],[20,50,4,1.623],[20,44,2,1.482],[20,38,4,1.532],[20,36,4,1.22],[20,47,4,1.725],[15,37,5,1.515],[15,18,6,0.274],[15,16,9,-0.163],[15,46,5,1.466],[15,30,5,1.014],[15,41,5,1.013],[15,34,6,1.594],[15,26,2,0.02],[15,19,5,0.039],[15,7,5,-0.523],[15,24,5,0.514],[15,6,5,-0.629],[15,12,12,0.043],[15,48,5,2.02],[15,31,5,1.223],[15,13,6,-0.356],[15,10,6,-0.2],[15,45,5,1.841],[15,17,12,0.114],[15,27,5,0.616],[15,4,5,-0.918],[15,32,5,0.539],[15,11,6,-0.57],[15,28,5,1.131],[15,50,5,1.879],[15,8,5,-0.744],[15,14,12,0.152],[15,38,5,1.19],[15,21,8,0.708],[15,36,5,0.944],[15,47,5,1.407],[49,51,4,0.02],[49,30,2,-1.295],[49,29,2,-1.285],[49,42,4,-0.363],[49,40,4,-0.097],[49,43,3,0.38],[49,39,3,-0.831],[49,44,3,-0.198],[49,36,4,-1.113],[37,18,2,-0.535],[37,46,5,0.652],[37,30,3,-1.002],[37,41,4,-0.08],[37,34,2,1.133],[37,19,5,-0.705],[37,25,4,-0.374],[37,22,3,-1.168],[37,24,4,-0.708],[37,6,5,-1.819],[37,48,2,0.751],[37,31,5,-0.418],[37,13,2,-0.011],[37,45,2,-0.157],[37,35,2,-0.059],[37,27,4,-0.784],[37,4,5,-2.02],[37,32,4,-0.562],[37,28,5,-0.727],[37,50,2,1.378],[37,8,5,-1.591],[37,44,2,0.282],[37,33,4,-0.336],[37,38,6,-0.428],[37,21,2,-1.158],[37,36,5,-0.366],[37,47,6,0.617],[18,16,15,0.027],[18,30,3,0.83],[18,41,2,1.106],[18,34,7,1.414],[18,26,11,0.47],[18,19,6,0.01],[18,7,5,-0.8],[18,6,10,-0.844],[18,12,11,-0.396],[18,31,3,0.5],[18,13,7,-0.388],[18,10,2,0.079],[18,17,12,-0.249],[18,4,10,-1.251],[18,32,3,0.86],[18,11,2,-0.495],[18,28,3,0.996],[18,8,10,-0.526],[18,14,10,-0.224],[18,21,6,0.323],[18,36,2,1.107],[16,26,4,0.721],[16,7,4,-0.523],[16,6,4,-0.759],[16,13,4,-0.185],[16,10,5,-0.395],[16,17,12,0.405],[16,4,3,-1.392],[16,11,5,-0.4],[16,14,12,-0.024],[16,21,12,0.434],[53,30,2,-1.93],[53,29,2,-1.53],[53,36,4,-1.862],[46,30,6,-1.205],[46,41,6,-0.229],[46,26,2,-0.644],[46,19,5,-1.587],[46,7,2,-2.038],[46,25,6,-1.437],[46,22,5,-1.365],[46,24,6,-1.242],[46,6,5,-1.511],[46,12,2,-1.262],[46,48,6,0.587],[46,31,5,-0.901],[46,45,6,-0.727],[46,17,2,-1.566],[46,27,6,-1.208],[46,4,5,-1.974],[46,32,5,-1.073],[46,39,6,-0.234],[46,28,5,-1.337],[46,50,5,1.236],[46,8,5,-1.873],[46,14,2,-1.839],[46,44,5,0.149],[46,33,5,-0.577],[46,38,5,-0.816],[46,21,2,-1.709],[46,36,5,-0.341],[46,47,5,-0.07],[51,30,2,-1.483],[51,29,2,-1.33],[51,42,4,-0.776],[51,43,1,0.586],[51,39,4,-1.263],[51,44,4,-0.521],[51,36,4,-0.972],[30,41,4,0.515],[30,34,3,0.126],[30,26,5,-0.579],[30,19,5,-0.823],[30,7,5,-1.287],[30,25,5,-0.561],[30,22,6,-0.985],[30,29,8,-0.487],[30,24,5,-0.631],[30,6,5,-1.333],[30,12,5,-1.34],[30,42,2,0.898],[30,40,2,1.313],[30,48,3,1.102],[30,31,5,0.608],[30,13,3,-1.283],[30,45,2,0.713],[30,17,5,-0.509],[30,35,4,0.075],[30,27,5,-0.148],[30,4,5,-1.842],[30,43,1,1.286],[30,32,3,0.057],[30,39,2,0.747],[30,28,5,0.188],[30,50,2,0.945],[30,8,5,-1.257],[30,14,5,-1.13],[30,44,3,1.23],[30,33,3,0.064],[30,38,6,0.469],[30,21,4,-0.693],[30,36,2,0.869],[30,47,5,0.778],[41,34,2,-0.789],[41,19,5,-0.95],[41,25,4,-0.419],[41,24,4,-1.427],[41,6,5,-1.879],[41,48,4,0.128],[41,31,5,-0.841],[41,13,2,-1.585],[41,45,4,0.367],[41,27,4,-1.107],[41,4,5,-2.141],[41,32,4,-0.647],[41,39,4,0.041],[41,28,5,-1.141],[41,50,4,0.526],[41,8,5,-1.592],[41,33,4,-0.944],[41,38,6,-0.595],[41,21,2,-1.809],[41,36,4,-0.45],[41,47,6,0.141],[34,26,18,-0.477],[34,19,6,-0.68],[34,6,10,-1.367],[34,31,3,-0.596],[34,13,7,-1.41],[34,4,10,-1.695],[34,32,2,-0.757],[34,28,3,-0.7],[34,8,10,-1.544],[34,21,6,-0.735],[34,36,2,-0.295],[26,19,11,-0.707],[26,7,6,-1.248],[26,6,3,-1.001],[26,12,5,-1.063],[26,13,2,-1.215],[26,10,2,-0.943],[26,17,10,-0.863],[26,4,3,-1.041],[26,32,5,0.534],[26,11,1,-1.752],[26,28,10,-0.374],[26,50,2,2.074],[26,8,2,-0.953],[26,14,8,-0.914],[26,21,10,-0.217],[26,36,2,0.139],[26,47,1,0.144],[19,7,10,-0.762],[19,25,5,0.62],[19,24,5,0.965],[19,6,5,-0.737],[19,48,5,1.281],[19,31,5,0.674],[19,13,6,-0.054],[19,45,5,1.78],[19,17,11,-0.092],[19,27,5,0.594],[19,4,5,-1.013],[19,32,4,0.509],[19,39,5,0.787],[19,28,5,0.327],[19,50,5,1.843],[19,8,5,-0.55],[19,14,1,-0.021],[19,38,5,0.829],[19,21,8,0.319],[19,36,5,1.166],[19,47,5,1.397],[7,6,5,-0.044],[7,12,7,0.566],[7,13,5,-0.215],[7,10,11,-0.119],[7,17,6,0.488],[7,4,5,-0.821],[7,32,4,1.912],[7,11,4,0.065],[7,28,5,1.608],[7,50,2,1.786],[7,14,6,0.016],[7,21,5,0.847],[7,36,2,1.887],[7,47,1,2.17],[25,22,3,-0.555],[25,24,7,-0.016],[25,48,2,1.338],[25,45,2,0.68],[25,35,2,0.251],[25,27,7,-0.026],[25,32,7,0.062],[25,50,2,1.201],[25,44,2,1.379],[25,33,7,0.449],[25,38,5,1.195],[25,47,4,1.535],[22,29,6,0.294],[22,24,3,0.089],[22,52,4,1.837],[22,40,4,1.396],[22,48,3,1.58],[22,45,2,0.918],[22,35,5,0.895],[22,27,3,0.864],[22,55,4,2.798],[22,32,3,1.001],[22,39,4,1.13],[22,54,2,2.243],[22,50,2,1.548],[22,44,2,1.419],[22,33,3,0.55],[22,38,5,1.604],[22,36,4,0.962],[22,47,5,1.512],[29,52,4,1.732],[29,42,2,1.101],[29,40,4,0.791],[29,35,7,0.393],[29,55,4,2.688],[29,43,2,0.539],[29,39,4,0.154],[29,54,4,2.013],[29,44,2,1.147],[29,36,6,0.355],[24,6,5,-0.627],[24,48,2,1.464],[24,31,5,0.509],[24,45,2,0.724],[24,35,2,1.166],[24,27,7,0.237],[24,32,7,0.205],[24,28,5,0.148],[24,50,2,1.337],[24,8,5,-1.037],[24,44,2,1.383],[24,33,7,0.381],[24,38,6,1.286],[24,47,5,1.076],[6,12,20,0.508],[6,31,5,1.39],[6,13,10,0.381],[6,10,4,0.43],[6,45,5,1.9],[6,17,12,0.882],[6,27,4,1.307],[6,4,5,-0.445],[6,32,5,0.789],[6,11,4,0.548],[6,28,5,1.344],[6,50,5,1.931],[6,8,5,-0.28],[6,14,13,0.55],[6,38,5,1.615],[6,21,11,0.946],[6,36,5,1.645],[6,47,5,2.115],[12,13,13,0.195],[12,10,7,0.177],[12,17,12,0.286],[12,4,4,-1.402],[12,32,5,1.275],[12,11,6,0.075],[12,28,5,0.969],[12,50,2,1.948],[12,14,13,0.242],[12,21,5,0.543],[12,36,2,1.047],[12,47,2,1.859],[52,35,3,-1.617],[52,55,4,1.888],[52,54,4,0.578],[42,40,4,-0.296],[42,43,1,-0.107],[42,39,4,-0.277],[42,44,4,-0.324],[42,36,4,-0.745],[40,35,3,-0.442],[40,43,2,0.61],[40,39,4,-0.689],[40,44,4,0.122],[40,36,2,-0.687],[48,31,5,-0.954],[48,45,2,-0.841],[48,35,2,-0.851],[48,27,2,-0.887],[48,32,2,-1.694],[48,28,5,-1.294],[48,50,2,-0.005],[48,44,2,-0.512],[48,33,2,-1.245],[48,38,6,-0.797],[48,47,5,-0.516],[31,13,3,-0.782],[31,45,5,1.117],[31,27,5,-0.762],[31,4,5,-1.681],[31,32,5,0.153],[31,28,5,0.121],[31,50,5,1.189],[31,8,5,-1.523],[31,38,5,0.801],[31,21,4,-0.187],[31,36,5,0.896],[31,47,5,1.336],[13,10,20,-0.331],[13,17,13,0.126],[13,4,10,-0.718],[13,32,2,1.447],[13,11,9,0.135],[13,28,3,0.947],[13,8,10,-0.576],[13,14,12,-0.026],[13,21,6,0.284],[13,36,2,0.778],[10,17,9,0.569],[10,4,4,-1.024],[10,11,5,0.0],[10,14,10,0.306],[45,17,16,-1.384],[45,35,2,-0.95],[45,27,1,-1.449],[45,4,5,-2.261],[45,32,2,-1.177],[45,28,5,-1.495],[45,50,2,0.57],[45,8,5,-2.109],[45,44,2,0.084],[45,33,2,-0.155],[45,38,6,-0.638],[45,36,5,-0.984],[45,47,6,-0.5],[17,4,4,-0.487],[17,32,5,1.134],[17,11,7,-0.407],[17,28,5,0.646],[17,50,2,1.891],[17,8,2,0.025],[17,14,12,-0.27],[17,21,5,0.689],[17,36,2,0.888],[17,47,2,2.248],[35,27,2,-0.247],[35,55,1,2.925],[35,43,2,0.85],[35,32,1,0.926],[35,39,3,0.492],[35,54,1,1.725],[35,50,2,0.334],[35,44,2,1.126],[35,33,2,-0.087],[35,36,2,0.787],[27,4,5,-1.876],[27,32,7,-0.019],[27,28,5,-0.177],[27,50,2,1.591],[27,8,5,-0.719],[27,44,2,1.058],[27,33,5,0.691],[27,38,6,0.759],[27,36,5,0.543],[27,47,6,1.097],[4,32,5,1.859],[4,11,3,1.027],[4,28,4,1.454],[4,50,5,2.206],[4,8,5,0.478],[4,14,3,0.806],[4,38,5,2.112],[4,21,12,1.154],[4,36,5,1.87],[4,47,5,2.18],[55,54,4,-1.235],[43,39,3,-0.205],[43,44,1,-0.06],[43,36,4,-0.77],[32,11,19,-1.233],[32,28,5,-0.179],[32,50,2,1.492],[32,8,5,-1.497],[32,14,5,-0.468],[32,44,2,1.528],[32,33,5,0.084],[32,38,5,0.387],[32,21,4,-0.602],[32,36,4,-0.273],[32,47,5,0.457],[11,14,9,0.015],[11,21,2,0.371],[39,44,4,0.275],[39,38,6,-0.254],[39,36,2,-0.168],[39,47,5,0.121],[28,50,5,1.064],[28,8,5,-1.515],[28,14,5,-0.302],[28,38,5,0.55],[28,21,4,-0.678],[28,36,5,-0.106],[28,47,5,0.973],[50,8,5,-2.087],[50,14,2,-1.834],[50,44,2,-0.859],[50,33,2,-1.332],[50,38,6,-0.623],[50,36,4,-1.322],[50,47,6,-0.237],[8,14,18,0.404],[8,38,5,1.671],[8,21,12,0.706],[8,36,5,1.782],[8,47,5,2.195],[14,21,5,0.202],[14,36,2,1.165],[14,47,2,2.03],[44,33,2,-0.945],[44,38,5,-0.557],[44,36,4,-0.54],[44,47,5,0.361],[33,38,6,0.457],[33,47,6,0.637],[38,36,6,0.025],[38,47,5,0.793],[21,36,2,0.787],[36,47,5,0.774]]}},"connections":{"title":"Extended Connections","metric":{"name":"Quadratic-v1 score","scale":"Mean of (exact groups / 4)^2 per puzzle × 100; 0, 1, 2, 3, 4 groups earn 0, 6.25, 25, 56.25, 100","interval":null,"count":"Puzzles attempted"},"description":"940 NYT Connections puzzles with up to four extra trick words added to each, testing verbal associative reasoning under plausible decoys. One attempt per puzzle.","sourceUrl":"https://github.com/lechmazur/nyt-connections","readmeUrl":"https://github.com/lechmazur/nyt-connections/blob/b69dd13782375eb3b95fc0ed06318dd5f938a7ee/README.md","snapshotDate":"2026-10-08","sourceCommit":"b69dd13782375eb3b95fc0ed06318dd5f938a7ee","sourceCommitDate":"2026-10-08T18:18:34-04:00","sourceFiles":{"README.md":"27a51124bef49ded","source grade_results_quadratic.csv":"0d3b2809213ce405","source grade_results_latest_quadratic.csv":"ab35fbf8b984b936","source grade_results_legacy_quadratic.csv":"06886dfb78d3d44b"},"cohorts":{"main":{"label":"All 940 puzzles","puzzles":940,"fullCoverageOnly":true},"newest100":{"label":"Newest 100 puzzles","puzzles":100,"fullCoverageOnly":true,"note":"Same models and scoring on the newest puzzles, to check for training-data exposure."},"partial":{"label":"Older or incomplete runs","note":"Fewer than 940 puzzles; puzzle sets differ by run, so scores are not comparable with the main board or with each other."}},"notes":["The published charts shade uncertainty; the tables do not give numeric ranges.","Puzzles that a model refused, or that were blocked, are scored as 0 of 4 groups.","Main and newest-100 boards include only models that completed all 940 puzzles."],"models":[{"id":"gpt-6-astra-xhigh","name":"GPT-6 Astra (xhigh reasoning)","rank":1,"score":98.1,"count":940,"newest100":{"rank":1,"score":98.7}},{"id":"gpt-6-astra-high","name":"GPT-6 Astra (high reasoning)","rank":2,"score":97.7,"count":940,"newest100":{"rank":2,"score":97.8}},{"id":"gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","rank":3,"score":97.4,"count":940,"newest100":{"rank":4,"score":96.1}},{"id":"gemini-3.8-flash-high","name":"Gemini 3.8 Flash (high reasoning)","rank":4,"score":97.4,"count":940,"newest100":{"rank":3,"score":96.5}},{"id":"gpt-5.5-xhigh","name":"GPT-5.5 (xhigh reasoning)","rank":5,"score":96.2,"count":940,"newest100":{"rank":5,"score":96.1}},{"id":"gpt-6.1-sol-high","name":"GPT-6.1 Sol (high reasoning)","rank":6,"score":95.5,"count":940,"newest100":{"rank":6,"score":95.6}},{"id":"gpt-5.5-high","name":"GPT-5.5 (high reasoning)","rank":7,"score":95.2,"count":940,"newest100":{"rank":7,"score":95.2}},{"id":"gemini-3-pro-preview","name":"Gemini 3 Pro Preview","rank":8,"score":94.4,"count":940,"newest100":{"rank":13,"score":92.3}},{"id":"claude-opus-5-xhigh","name":"Claude Opus 5 (xhigh reasoning)","rank":9,"score":94.3,"count":940,"newest100":{"rank":8,"score":94.5}},{"id":"gemini-3.7-flash","name":"Gemini 3.7 Flash","rank":10,"score":94.0,"count":940,"newest100":{"rank":14,"score":92.2}},{"id":"gpt-5.6-xhigh","name":"GPT-5.6 Sol (xhigh reasoning)","rank":11,"score":93.8,"count":940,"newest100":{"rank":9,"score":94.4}},{"id":"kimi-k3","name":"Kimi K3","rank":12,"score":93.6,"count":940,"newest100":{"rank":16,"score":92.1}},{"id":"claude-fable-5-high","name":"Claude Fable 5 (high reasoning)","rank":13,"score":92.7,"count":940,"newest100":{"rank":10,"score":93.6}},{"id":"gemini-3.5-flash","name":"Gemini 3.5 Flash","rank":14,"score":92.6,"count":940,"newest100":{"rank":18,"score":90.8}},{"id":"gpt-5.5-medium","name":"GPT-5.5 (medium reasoning)","rank":15,"score":92.4,"count":940,"newest100":{"rank":28,"score":87.3}},{"id":"claude-opus-5-high","name":"Claude Opus 5 (high reasoning)","rank":16,"score":92.2,"count":940,"newest100":{"rank":17,"score":91.9}},{"id":"claude-opus-4-6-adaptive","name":"Claude Opus 4.6 (high reasoning)","rank":17,"score":92.1,"count":940,"newest100":{"rank":27,"score":88.1}},{"id":"deepseek-v4-pro-high","name":"DeepSeek V4 Pro (high reasoning)","rank":18,"score":91.3,"count":940,"newest100":{"rank":25,"score":88.4}},{"id":"gpt-5.4-xhigh","name":"GPT-5.4 (xhigh reasoning)","rank":19,"score":91.3,"count":940,"newest100":{"rank":11,"score":93.4}},{"id":"claude-opus-4-8-xhigh","name":"Claude Opus 4.8 (xhigh reasoning)","rank":20,"score":91.1,"count":940,"newest100":{"rank":19,"score":90.6}},{"id":"gpt-5.6-high","name":"GPT-5.6 Sol (high reasoning)","rank":21,"score":91.0,"count":940,"newest100":{"rank":12,"score":92.7}},{"id":"gpt-5.4-high","name":"GPT-5.4 (high reasoning)","rank":22,"score":90.6,"count":940,"newest100":{"rank":26,"score":88.4}},{"id":"gpt-6-sol-high","name":"GPT-6 Sol (high reasoning)","rank":23,"score":90.1,"count":940,"newest100":{"rank":22,"score":88.8}},{"id":"claude-fable-5-1-high","name":"Claude Fable 5.1 (high reasoning)","rank":24,"score":90.0,"count":940,"newest100":{"rank":23,"score":88.5}},{"id":"grok-4.20-multi-agent-experimental-beta-0304","name":"Grok 4.20 Multi-Agent Exp Beta 0304","rank":25,"score":89.6,"count":940,"newest100":{"rank":31,"score":85.2}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","rank":26,"score":89.6,"count":940,"newest100":{"rank":29,"score":87.2}},{"id":"deepseek-v4.1-flash-high","name":"DeepSeek V4.1 Flash (high reasoning)","rank":27,"score":89.6,"count":940,"newest100":{"rank":30,"score":86.1}},{"id":"gemini-3.6-flash","name":"Gemini 3.6 Flash","rank":28,"score":89.0,"count":940,"newest100":{"rank":24,"score":88.5}},{"id":"claude-opus-5-5-high","name":"Claude Opus 5.5 (high reasoning)","rank":29,"score":88.5,"count":940,"newest100":{"rank":20,"score":90.6}},{"id":"claude-opus-4-8-high","name":"Claude Opus 4.8 (high reasoning)","rank":30,"score":88.3,"count":940,"newest100":{"rank":15,"score":92.1}},{"id":"qwen3.8-max","name":"Qwen 3.8 Max","rank":31,"score":88.3,"count":940,"newest100":{"rank":21,"score":88.9}},{"id":"claude-opus-5-5","name":"Claude Opus 5.5 (medium reasoning)","rank":32,"score":87.8,"count":940,"newest100":{"rank":35,"score":83.4}},{"id":"gpt-5.4-medium","name":"GPT-5.4 (medium reasoning)","rank":33,"score":87.8,"count":940,"newest100":{"rank":33,"score":84.4}},{"id":"grok-4-1-fast-reasoning","name":"Grok 4.1 Fast Reasoning","rank":34,"score":87.4,"count":940,"newest100":{"rank":47,"score":75.2}},{"id":"kimi-k2.6","name":"Kimi K2.6","rank":35,"score":87.2,"count":940,"newest100":{"rank":36,"score":80.2}},{"id":"grok-4.20-beta-0309-reasoning","name":"Grok 4.20 0309 (Reasoning)","rank":36,"score":85.4,"count":940,"newest100":{"rank":42,"score":77.4}},{"id":"qwen3.7-max","name":"Qwen 3.7 Max","rank":37,"score":85.1,"count":940,"newest100":{"rank":38,"score":78.9}},{"id":"muse-spark-1.3-high","name":"Muse Spark 1.3 (high reasoning)","rank":38,"score":85.1,"count":940,"newest100":{"rank":34,"score":83.6}},{"id":"muse-spark-1.1-high","name":"Muse Spark 1.1 (high reasoning)","rank":39,"score":84.9,"count":940,"newest100":{"rank":32,"score":84.8}},{"id":"grok-4.20-experimental-beta-0304-reasoning","name":"Grok 4.20 Reasoning Exp Beta 0304","rank":40,"score":83.7,"count":940,"newest100":{"rank":45,"score":77.1}},{"id":"gpt-5.2-xhigh","name":"GPT-5.2 (xhigh reasoning)","rank":41,"score":83.6,"count":940,"newest100":{"rank":39,"score":78.6}},{"id":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","rank":42,"score":83.1,"count":940,"newest100":{"rank":69,"score":61.8}},{"id":"claude-sonnet-4-6-adaptive","name":"Claude Sonnet 4.6 (high reasoning)","rank":43,"score":80.9,"count":940,"newest100":{"rank":49,"score":74.1}},{"id":"claude-sonnet-5-5-high","name":"Claude Sonnet 5.5 (high reasoning)","rank":44,"score":80.5,"count":940,"newest100":{"rank":37,"score":79.1}},{"id":"grok-4.6-xhigh","name":"Grok 4.6 (xhigh reasoning)","rank":45,"score":80.0,"count":940,"newest100":{"rank":46,"score":77.1}},{"id":"grok-4.5-high","name":"Grok 4.5 (high reasoning)","rank":46,"score":79.9,"count":940,"newest100":{"rank":44,"score":77.2}},{"id":"gpt-5.2-pro","name":"GPT-5.2 Pro","rank":47,"score":79.3,"count":940,"newest100":{"rank":54,"score":71.8}},{"id":"muse-spark-1.2-high","name":"Muse Spark 1.2 (high reasoning)","rank":48,"score":79.2,"count":940,"newest100":{"rank":43,"score":77.2}},{"id":"grok-4.6-high","name":"Grok 4.6 (high reasoning)","rank":49,"score":79.0,"count":940,"newest100":{"rank":48,"score":74.6}},{"id":"gpt-5.6-terra-high","name":"GPT-5.6 Terra (high reasoning)","rank":50,"score":78.4,"count":940,"newest100":{"rank":52,"score":72.4}},{"id":"glm-5.1","name":"GLM-5.1","rank":51,"score":77.7,"count":940,"newest100":{"rank":41,"score":77.6}},{"id":"grok-4.7-high","name":"Grok 4.7 (high reasoning)","rank":52,"score":76.8,"count":940,"newest100":{"rank":51,"score":72.8}},{"id":"claude-sonnet-4-6-32K","name":"Claude Sonnet 4.6 Thinking 32K","rank":53,"score":76.4,"count":940,"newest100":{"rank":57,"score":69.4}},{"id":"claude-opus-4-6-16K","name":"Claude Opus 4.6 Thinking 16K","rank":54,"score":76.4,"count":940,"newest100":{"rank":40,"score":78.4}},{"id":"claude-sonnet-5-high","name":"Claude Sonnet 5 (high reasoning)","rank":55,"score":75.1,"count":940,"newest100":{"rank":56,"score":69.9}},{"id":"glm-5","name":"GLM-5","rank":56,"score":74.8,"count":940,"newest100":{"rank":59,"score":67.5}},{"id":"qwen3.7-plus","name":"Qwen 3.7 Plus","rank":57,"score":74.8,"count":940,"newest100":{"rank":55,"score":70.9}},{"id":"glm-5-2-high","name":"GLM-5.2 (high reasoning)","rank":58,"score":74.3,"count":940,"newest100":{"rank":50,"score":72.8}},{"id":"glm-5.3-high","name":"GLM-5.3 (high reasoning)","rank":59,"score":74.2,"count":940,"newest100":{"rank":53,"score":72.2}},{"id":"qwen3.6-max-preview","name":"Qwen 3.6 Max Preview","rank":60,"score":74.1,"count":940,"newest100":{"rank":58,"score":69.4}},{"id":"gemma-4-31b-it-reasoning","name":"Gemma 4 31B Reasoning","rank":61,"score":70.6,"count":940,"newest100":{"rank":62,"score":65.9}},{"id":"kimi-k2.5","name":"Kimi K2.5 Thinking","rank":62,"score":69.9,"count":940,"newest100":{"rank":66,"score":63.7}},{"id":"gpt-5.6-luna-high","name":"GPT-5.6 Luna (high reasoning)","rank":63,"score":69.4,"count":940,"newest100":{"rank":61,"score":66.1}},{"id":"gpt-6-luna-high","name":"GPT-6 Luna (high reasoning)","rank":64,"score":68.7,"count":940,"newest100":{"rank":63,"score":65.8}},{"id":"hy4-preview","name":"Tencent Hy4 Preview","rank":65,"score":68.2,"count":940,"newest100":{"rank":65,"score":64.2}},{"id":"gpt-5.2-high","name":"GPT-5.2 (high reasoning)","rank":66,"score":68.1,"count":940,"newest100":{"rank":60,"score":66.2}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro Preview","rank":67,"score":67.3,"count":940,"newest100":{"rank":71,"score":59.9}},{"id":"claude-haiku-5-5-high","name":"Claude Haiku 5.5 (high reasoning)","rank":68,"score":65.7,"count":940,"newest100":{"rank":64,"score":64.9}},{"id":"minimax-m3","name":"MiniMax-M3","rank":69,"score":65.1,"count":940,"newest100":{"rank":67,"score":63.4}},{"id":"gpt-5.4-mini-xhigh","name":"GPT-5.4 Mini (xhigh reasoning)","rank":70,"score":61.8,"count":940,"newest100":{"rank":68,"score":62.5}},{"id":"gpt-5.2-medium","name":"GPT-5.2 (medium reasoning)","rank":71,"score":60.6,"count":940,"newest100":{"rank":73,"score":55.8}},{"id":"gemini-3.5-flash-lite-high","name":"Gemini 3.5 Flash-Lite (high reasoning)","rank":72,"score":60.4,"count":940,"newest100":{"rank":70,"score":60.7}},{"id":"qwen3.6-plus","name":"Qwen 3.6 Plus","rank":73,"score":60.3,"count":940,"newest100":{"rank":72,"score":57.1}},{"id":"qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","rank":74,"score":58.9,"count":940,"newest100":{"rank":76,"score":47.1}},{"id":"grok-4.3","name":"Grok 4.3","rank":75,"score":55.2,"count":940,"newest100":{"rank":78,"score":45.6}},{"id":"qwen3.8-27b","name":"Qwen3.8-27B","rank":76,"score":54.5,"count":940,"newest100":{"rank":74,"score":52.0}},{"id":"gpt-5.2-low","name":"GPT-5.2 (low reasoning)","rank":77,"score":54.2,"count":940,"newest100":{"rank":77,"score":46.4}},{"id":"claude-opus-4-5-20251101-16K","name":"Claude Opus 4.5 Thinking 16K","rank":78,"score":52.5,"count":940,"newest100":{"rank":75,"score":51.6}},{"id":"qwen3.5-122b-a10b","name":"Qwen3.5-122B-A10B","rank":79,"score":51.7,"count":940,"newest100":{"rank":79,"score":45.4}},{"id":"claude-opus-4-5-20251101-0K","name":"Claude Opus 4.5 (no reasoning)","rank":80,"score":49.4,"count":940,"newest100":{"rank":84,"score":42.0}},{"id":"claude-sonnet-4-6-16K","name":"Claude Sonnet 4.6 Thinking 16K","rank":81,"score":48.0,"count":940,"newest100":{"rank":80,"score":45.3}},{"id":"qwen3.5-27b","name":"Qwen3.5-27B","rank":82,"score":47.9,"count":940,"newest100":{"rank":81,"score":44.6}},{"id":"claude-sonnet-4-6-0K","name":"Claude Sonnet 4.6 (no reasoning)","rank":83,"score":44.8,"count":940,"newest100":{"rank":86,"score":40.4}},{"id":"qwen3.7-flash","name":"Qwen 3.7 Flash","rank":84,"score":43.8,"count":940,"newest100":{"rank":91,"score":35.4}},{"id":"claude-opus-4-6-0K","name":"Claude Opus 4.6 (no reasoning)","rank":85,"score":43.2,"count":940,"newest100":{"rank":89,"score":37.2}},{"id":"qwen3.6-35b-a3b","name":"Qwen3.6-35B-A3B","rank":86,"score":41.6,"count":940,"newest100":{"rank":90,"score":35.5}},{"id":"hy3-high","name":"Tencent Hy3 (high)","rank":87,"score":41.2,"count":940,"newest100":{"rank":85,"score":40.6}},{"id":"step-3.7-flash-high","name":"Step 3.7 Flash (high reasoning)","rank":88,"score":39.7,"count":940,"newest100":{"rank":92,"score":34.2}},{"id":"claude-opus-4-7-adaptive","name":"Claude Opus 4.7 (high reasoning)","rank":89,"score":39.0,"count":940,"newest100":{"rank":87,"score":39.3}},{"id":"claude-sonnet-4-5-20250929-16K","name":"Claude Sonnet 4.5 Thinking 16K","rank":90,"score":37.3,"count":940,"newest100":{"rank":83,"score":43.0}},{"id":"deepseek-v32-exp","name":"DeepSeek V3.2","rank":91,"score":36.7,"count":940,"newest100":{"rank":95,"score":29.7}},{"id":"claude-sonnet-4-5-20250929-0K","name":"Claude Sonnet 4.5 (no reasoning)","rank":92,"score":35.8,"count":940,"newest100":{"rank":82,"score":43.6}},{"id":"mimo-v2.5-pro","name":"Xiaomi MiMo V2.5 Pro","rank":93,"score":34.4,"count":940,"newest100":{"rank":94,"score":31.4}},{"id":"qwen3-max-2026-01-23","name":"Qwen3 Max (2026-01-23)","rank":94,"score":30.1,"count":940,"newest100":{"rank":93,"score":31.6}},{"id":"step-3.5-flash","name":"Step 3.5 Flash","rank":95,"score":28.4,"count":940,"newest100":{"rank":99,"score":22.8}},{"id":"seed-2.0-pro","name":"ByteDance Seed2.0 Pro","rank":96,"score":28.4,"count":940,"newest100":{"rank":97,"score":28.0}},{"id":"mistral-large-4-high","name":"Mistral Large 4 (high)","rank":97,"score":27.4,"count":940,"newest100":{"rank":98,"score":27.2}},{"id":"mimo-v2-pro","name":"Xiaomi MiMo V2 Pro","rank":98,"score":25.8,"count":940,"newest100":{"rank":100,"score":22.0}},{"id":"minimax-m2.7","name":"MiniMax-M2.7","rank":99,"score":24.7,"count":940,"newest100":{"rank":96,"score":28.6}},{"id":"ernie-5.1","name":"Baidu Ernie 5.1","rank":100,"score":23.4,"count":940,"newest100":{"rank":101,"score":20.0}},{"id":"gpt-5.5-none","name":"GPT-5.5 (no reasoning)","rank":101,"score":22.0,"count":940,"newest100":{"rank":103,"score":19.1}},{"id":"gpt-5.4-none","name":"GPT-5.4 (no reasoning)","rank":102,"score":17.8,"count":940,"newest100":{"rank":102,"score":19.8}},{"id":"longcat-flash-thinking","name":"LongCat Flash Thinking","rank":103,"score":17.7,"count":940,"newest100":{"rank":105,"score":17.3}},{"id":"hy3-preview","name":"Tencent Hy3 Preview","rank":104,"score":17.2,"count":940,"newest100":{"rank":104,"score":18.9}},{"id":"minimax-m2.5","name":"MiniMax-M2.5","rank":105,"score":16.8,"count":940,"newest100":{"rank":107,"score":16.2}},{"id":"trinity-large-thinking","name":"Arcee Trinity Large Thinking","rank":106,"score":16.5,"count":940,"newest100":{"rank":106,"score":16.9}},{"id":"gemma-4-31b-it","name":"Gemma 4 31B IT","rank":107,"score":15.7,"count":940,"newest100":{"rank":109,"score":15.7}},{"id":"nemotron-3-super","name":"Nemotron 3 Super","rank":108,"score":15.4,"count":940,"newest100":{"rank":112,"score":12.4}},{"id":"minimax-m2","name":"MiniMax-M2","rank":109,"score":14.8,"count":940,"newest100":{"rank":114,"score":11.9}},{"id":"gpt-5.2-none","name":"GPT-5.2 (no reasoning)","rank":110,"score":14.5,"count":940,"newest100":{"rank":108,"score":15.8}},{"id":"haiku45","name":"Claude 4.5 Haiku","rank":111,"score":14.3,"count":940,"newest100":{"rank":88,"score":37.5}},{"id":"mistral-medium-3.5-high","name":"Mistral Medium 3.5 (high)","rank":112,"score":12.9,"count":940,"newest100":{"rank":110,"score":14.6}},{"id":"grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast Non-Reasoning","rank":113,"score":12.3,"count":940,"newest100":{"rank":120,"score":8.8}},{"id":"qwen3-max-thinking","name":"Qwen 3 Max Thinking","rank":114,"score":11.8,"count":940,"newest100":{"rank":115,"score":11.6}},{"id":"minimax-m2.1","name":"MiniMax-M2.1","rank":115,"score":11.2,"count":940,"newest100":{"rank":111,"score":12.8}},{"id":"claude-opus-4-7-0K","name":"Claude Opus 4.7 (no reasoning)","rank":116,"score":10.8,"count":940,"newest100":{"rank":113,"score":11.9}},{"id":"ernie-5","name":"Baidu Ernie 5.0","rank":117,"score":10.3,"count":940,"newest100":{"rank":116,"score":10.7}},{"id":"grok-4.20-0309-non-reasoning","name":"Grok 4.20 0309 (Non-Reasoning)","rank":118,"score":8.6,"count":940,"newest100":{"rank":117,"score":9.4}},{"id":"deepseek-v32-exp-non-reasoning","name":"DeepSeek V3.2 (no reasoning)","rank":119,"score":8.2,"count":940,"newest100":{"rank":125,"score":6.8}},{"id":"gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash-Lite Preview","rank":120,"score":8.2,"count":940,"newest100":{"rank":119,"score":8.9}},{"id":"llama4-maverick","name":"Llama 4 Maverick","rank":121,"score":8.0,"count":940,"newest100":{"rank":122,"score":8.1}},{"id":"grok-4.20-experimental-beta-0304-non-reasoning","name":"Grok 4.20 Non-Reasoning Exp Beta 0304","rank":122,"score":7.6,"count":940,"newest100":{"rank":123,"score":7.7}},{"id":"mistral-large-2512","name":"Mistral Large 3","rank":123,"score":7.5,"count":940,"newest100":{"rank":118,"score":8.9}},{"id":"hy3","name":"Tencent Hy3 (non-thinking)","rank":124,"score":6.9,"count":940,"newest100":{"rank":121,"score":8.2}},{"id":"mistral-medium-2508","name":"Mistral Medium 3.1","rank":125,"score":6.5,"count":940,"newest100":{"rank":124,"score":7.1}},{"id":"ling-2.6-1t","name":"Ling 2.6 1T","rank":126,"score":4.1,"count":940,"newest100":{"rank":126,"score":5.5}}],"partial":[{"id":"seed-2.1-pro","name":"ByteDance Seed2.1 Pro","rank":1,"score":97.8,"count":101,"coverage":{"completed":101,"planned":940,"unit":"puzzles"}},{"id":"glm-5-2","name":"GLM-5.2 (max reasoning)","rank":2,"score":89.5,"count":194,"coverage":{"completed":194,"planned":940,"unit":"puzzles"}},{"id":"sherlock-think-alpha","name":"Sherlock Think Alpha","rank":3,"score":89.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwen3.8-max-0902","name":"Qwen 3.8 Max 0902","rank":4,"score":88.8,"count":919,"coverage":{"completed":919,"planned":940,"unit":"puzzles"}},{"id":"grok-4-fast-reasoning","name":"Grok 4 Fast Reasoning","rank":5,"score":88.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"inkling-high","name":"Inkling (high reasoning)","rank":6,"score":88.0,"count":136,"coverage":{"completed":136,"planned":940,"unit":"puzzles"}},{"id":"grok-4-0709","name":"Grok 4","rank":7,"score":87.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"sonoma-sky-alpha","name":"Sonoma Sky Alpha","rank":8,"score":86.5,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"mimo-v2.6-pro","name":"Xiaomi MiMo V2.6 Pro (thinking)","rank":9,"score":84.0,"count":27,"coverage":{"completed":27,"planned":940,"unit":"puzzles"}},{"id":"o3-pro-medium","name":"o3-pro (medium reasoning)","rank":10,"score":81.7,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-5-pro","name":"GPT-5 Pro","rank":11,"score":77.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"glm-5.2-max","name":"GLM-5.2 (max reasoning)","rank":12,"score":75.9,"count":211,"coverage":{"completed":211,"planned":940,"unit":"puzzles"}},{"id":"o1-pro","name":"o1-pro (medium reasoning)","rank":13,"score":74.6,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"o3-high","name":"o3 (high reasoning)","rank":14,"score":70.5,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-5-high","name":"GPT-5 (high reasoning)","rank":15,"score":67.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"o4-mini-high","name":"o4-mini (high reasoning)","rank":16,"score":64.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"ox-alpha","name":"Ox Alpha (max reasoning)","rank":17,"score":63.5,"count":217,"coverage":{"completed":217,"planned":940,"unit":"puzzles"}},{"id":"o3","name":"o3 (medium reasoning)","rank":18,"score":63.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-5-medium","name":"GPT-5 (medium reasoning)","rank":19,"score":61.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"o1-2024-12-17","name":"o1 (medium reasoning)","rank":20,"score":60.1,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gpt-5.1-high","name":"GPT-5.1 (high reasoning)","rank":21,"score":59.7,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"o4-mini","name":"o4-mini (medium reasoning)","rank":22,"score":58.4,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gpt-5-mini-medium","name":"GPT-5 mini (medium reasoning)","rank":23,"score":54.9,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-5-low","name":"GPT-5 (low reasoning)","rank":24,"score":53.2,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-5.1-medium","name":"GPT-5.1 (medium reasoning)","rank":25,"score":51.2,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"o3-mini-high","name":"o3-mini (high reasoning)","rank":26,"score":49.0,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"glm-4.7","name":"GLM-4.7","rank":27,"score":47.2,"count":767,"coverage":{"completed":767,"planned":940,"unit":"puzzles"}},{"id":"claude-opus-4-1-20250805-16K","name":"Claude Opus 4.1 Thinking 16K","rank":28,"score":45.3,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gemini-2.5-pro","name":"Gemini 2.5 Pro","rank":29,"score":44.9,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"kimi-k2-thinking","name":"Kimi K2 Thinking 64K","rank":30,"score":44.6,"count":924,"coverage":{"completed":924,"planned":940,"unit":"puzzles"}},{"id":"deepseek-reasoner","name":"DeepSeek V4 Flash (thinking)","rank":31,"score":43.9,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"o3-mini","name":"o3-mini (medium reasoning)","rank":32,"score":40.1,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gemini-2.5-pro-exp-03-25","name":"Gemini 2.5 Pro Exp 03-25","rank":33,"score":40.1,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"qwen3-235B","name":"Qwen 3 235B A22B","rank":34,"score":39.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"claude-opus-4-20250514-16K","name":"Claude Opus 4 Thinking 16K","rank":35,"score":35.2,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"r1-0528","name":"DeepSeek R1 05/28","rank":36,"score":33.6,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen 3 235B A22B 25-07 Think","rank":37,"score":31.6,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gemini-2_5-pro-preview-05-06","name":"Gemini 2.5 Pro Preview 05-06","rank":38,"score":28.1,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"claude-sonnet-4-20250514-16K","name":"Claude Sonnet 4 Thinking 16K","rank":39,"score":26.4,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"claude-sonnet-4-20250514-64K","name":"Claude Sonnet 4 Thinking 64K","rank":40,"score":26.0,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"r1-fireworks","name":"DeepSeek R1","rank":41,"score":24.4,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gpt-oss-120b","name":"GPT-OSS-120B","rank":42,"score":24.1,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"claude-opus-4-1-20250805-0K","name":"Claude Opus 4.1 (no reasoning)","rank":43,"score":21.7,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwen3-30b-a3b","name":"Qwen 3 30B A3B","rank":44,"score":21.2,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwen3-32B-or","name":"Qwen 3 32B","rank":45,"score":21.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwen3-30b-a3b-thinking-2507","name":"Qwen 3 30B A3B 25-07 Thinking","rank":46,"score":20.9,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"claude-3-7-sonnet-20250219-thinking","name":"Claude 3.7 Sonnet Thinking 16K","rank":47,"score":19.7,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"claude-opus-4-20250514-0K","name":"Claude Opus 4 (no reasoning)","rank":48,"score":19.7,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-4.5-preview-2025-02-27","name":"GPT-4.5 Preview","rank":49,"score":19.2,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"qwen3-next-80b-a3b-thinking","name":"Qwen 3 Next 80B A3B Thinking","rank":50,"score":18.5,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwq_fireworks","name":"Qwen QwQ-32B 16K","rank":51,"score":17.8,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"grok-3-mini-beta-high","name":"Grok 3 Mini Beta (high)","rank":52,"score":17.2,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"glm-4-5","name":"GLM-4.5","rank":53,"score":17.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"o1-mini","name":"o1-mini","rank":54,"score":14.1,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"grok-3-mini-beta","name":"Grok 3 Mini Beta (low)","rank":55,"score":14.0,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gpt-5-minimal","name":"GPT-5 (minimal reasoning)","rank":56,"score":13.9,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"claude-sonnet-4-20250514-0K","name":"Claude Sonnet 4 (no reasoning)","rank":57,"score":13.7,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"claude-opus-4-6-32K","name":"Claude Opus 4.6 Thinking 32K","rank":58,"score":13.6,"count":98,"coverage":{"completed":98,"planned":940,"unit":"puzzles"}},{"id":"command-a-reasoning","name":"Cohere Command A Reasoning","rank":59,"score":13.3,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gemini-flash-2-5-24k","name":"Gemini 2.5 Flash","rank":60,"score":12.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"grok-4-fast-non-reasoning","name":"Grok 4 Fast Non-Reasoning","rank":61,"score":12.5,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"glm-4-6","name":"GLM-4.6","rank":62,"score":12.5,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"sherlock-dash-alpha","name":"Sherlock Dash Alpha","rank":63,"score":12.2,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"quasar-alpha","name":"Quasar Alpha","rank":64,"score":12.1,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gemini_20_flash_thinking_exp_0121","name":"Gemini 2.0 Flash Think Exp 01-21","rank":65,"score":12.0,"count":649,"coverage":{"completed":649,"planned":940,"unit":"puzzles"}},{"id":"command-a-plus","name":"Cohere Command A+","rank":66,"score":12.0,"count":898,"coverage":{"completed":898,"planned":940,"unit":"puzzles"}},{"id":"chatgpt-4o-03-27","name":"GPT-4o Mar 2025","rank":67,"score":11.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwen3-max-preview","name":"Qwen 3 Max Preview","rank":68,"score":11.6,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gemini_20_pro_exp","name":"Gemini 2.0 Pro Exp 02-05","rank":69,"score":11.2,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"kimi-k2-0905","name":"Kimi K2-0905","rank":70,"score":11.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-4-1","name":"GPT-4.1","rank":71,"score":10.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"sonoma-dusk-alpha","name":"Sonoma Dusk Alpha","rank":72,"score":10.6,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"minimax-m1","name":"MiniMax-M1","rank":73,"score":10.5,"count":688,"coverage":{"completed":688,"planned":940,"unit":"puzzles"}},{"id":"chatgpt-4o-latest","name":"GPT-4o Feb 2025","rank":74,"score":10.3,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"polaris-alpha","name":"Polaris Alpha","rank":75,"score":10.2,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"deepseek-v31","name":"DeepSeek V3.1 Non-Think","rank":76,"score":10.1,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-5.1-none","name":"GPT-5.1 (no reasoning)","rank":77,"score":10.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"grok-3-beta","name":"Grok 3 Beta (no reasoning)","rank":78,"score":9.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"kimi-k2","name":"Kimi K2","rank":79,"score":8.9,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"claude-3-7-sonnet-20250219","name":"Claude 3.7 Sonnet","rank":80,"score":8.7,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gemini","name":"Gemini 1.5 Pro (Sept)","rank":81,"score":8.7,"count":601,"coverage":{"completed":601,"planned":940,"unit":"puzzles"}},{"id":"qwen3-235b-a22b-instruct-2507","name":"Qwen 3 235B A22B 25-07 Instruct","rank":82,"score":8.6,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-4o-2024-11-20","name":"GPT-4o 2024-11-20","rank":83,"score":8.6,"count":601,"coverage":{"completed":601,"planned":940,"unit":"puzzles"}},{"id":"grok2-12-12","name":"Grok 2 12-12","rank":84,"score":8.5,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gemini_20_flash","name":"Gemini 2.0 Flash","rank":85,"score":8.3,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"opus","name":"Claude 3 Opus","rank":86,"score":8.2,"count":650,"coverage":{"completed":650,"planned":940,"unit":"puzzles"}},{"id":"sonnet-20241022","name":"Claude 3.5 Sonnet 2024-10-22","rank":87,"score":8.1,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gpt-4o","name":"GPT-4o 2024-08-06","rank":88,"score":7.6,"count":601,"coverage":{"completed":601,"planned":940,"unit":"puzzles"}},{"id":"llama4-scout","name":"Llama 4 Scout","rank":89,"score":7.6,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwen-max","name":"Qwen 2.5 Max","rank":90,"score":7.6,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"deepseek-fireworks-v3-0324","name":"DeepSeek V3-0324","rank":91,"score":7.4,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"llama","name":"Llama 3.1 405B","rank":92,"score":6.7,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"ernie_4_5_300b_a47b","name":"Baidu Ernie 4.5 300B A47B","rank":93,"score":6.5,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"deepseek","name":"DeepSeek V4 Flash","rank":94,"score":6.2,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gpt-4-1-mini","name":"GPT-4.1 mini","rank":95,"score":6.1,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"llama33_70b","name":"Llama 3.3 70B","rank":96,"score":5.9,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"minimax","name":"MiniMax-Text-01","rank":97,"score":5.9,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"mistral-medium","name":"Mistral Medium 3.1","rank":98,"score":5.5,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"longcat_flash_chat","name":"LongCat Flash","rank":99,"score":5.2,"count":660,"coverage":{"completed":660,"planned":940,"unit":"puzzles"}},{"id":"command-a","name":"Cohere Command A","rank":100,"score":5.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"mistral","name":"Mistral Large 3","rank":101,"score":4.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"mistral-small-3-2","name":"Mistral Small 3.2","rank":102,"score":4.3,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gemma","name":"Gemma 2 27B","rank":103,"score":4.3,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"mistral-small-3-1","name":"Mistral Small 3.1","rank":104,"score":4.2,"count":651,"coverage":{"completed":651,"planned":940,"unit":"puzzles"}},{"id":"gemma3","name":"Gemma 3 27B","rank":105,"score":4.2,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"nova-pro","name":"Amazon Nova Pro","rank":106,"score":4.1,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"qwen","name":"Qwen 2.5 72B","rank":107,"score":4.0,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"haiku35","name":"Claude 3.5 Haiku","rank":108,"score":3.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"phi-4","name":"Microsoft Phi-4","rank":109,"score":3.4,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"gpt-4o_mini","name":"GPT-4o mini","rank":110,"score":3.4,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"mistral-small-2501","name":"Mistral Small 3","rank":111,"score":3.0,"count":601,"coverage":{"completed":601,"planned":940,"unit":"puzzles"}},{"id":"gpt-4-1-nano","name":"GPT-4.1 nano","rank":112,"score":2.8,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"glm4-32b-0414","name":"GLM4-32B-0414","rank":113,"score":2.7,"count":759,"coverage":{"completed":759,"planned":940,"unit":"puzzles"}},{"id":"claude_mini","name":"Claude 3 Haiku","rank":114,"score":0.7,"count":601,"coverage":{"completed":601,"planned":940,"unit":"puzzles"}}]}}
