{"updatedAt":"2026-09-27T15:35:03.611Z","size":"all","models":[{"rank":1,"model":"gpt-6-astra-xhigh","displayName":"GPT-6 Astra (xhigh)","familyDisplayName":"GPT-6 Astra","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-04T20:13:58.000Z","family":"gpt-6-astra","effort":"xhigh","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":100,"correct":30,"total":30,"totalCostUsd":10.81849},{"rank":2,"model":"gpt-6-astra-high","displayName":"GPT-6 Astra (high)","familyDisplayName":"GPT-6 Astra","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-04T20:13:58.000Z","family":"gpt-6-astra","effort":"high","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":96.7,"correct":29,"total":30,"totalCostUsd":8.28839},{"rank":3,"model":"claude-opus-5.5-high","displayName":"Claude Opus 5.5 (high)","familyDisplayName":"Claude Opus 5.5","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-22T16:32:12.000Z","family":"claude-opus-5.5","effort":"high","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":93.3,"correct":28,"total":30,"totalCostUsd":5.237496},{"rank":3,"model":"gpt-6-astra-max","displayName":"GPT-6 Astra (max)","familyDisplayName":"GPT-6 Astra","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-04T20:13:58.000Z","family":"gpt-6-astra","effort":"max","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":93.3,"correct":28,"total":30,"totalCostUsd":11.06394},{"rank":5,"model":"claude-opus-5.5-medium","displayName":"Claude Opus 5.5 (medium)","familyDisplayName":"Claude Opus 5.5","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-22T16:32:12.000Z","family":"claude-opus-5.5","effort":"medium","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":90,"correct":27,"total":30,"totalCostUsd":4.386696},{"rank":5,"model":"gpt-6-astra-medium","displayName":"GPT-6 Astra (medium)","familyDisplayName":"GPT-6 Astra","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-04T20:13:58.000Z","family":"gpt-6-astra","effort":"medium","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":90,"correct":27,"total":30,"totalCostUsd":8.21294},{"rank":7,"model":"gpt-6-sol-high","displayName":"GPT-6 Sol (high)","familyDisplayName":"GPT-6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:12:55.000Z","family":"gpt-6-sol","effort":"high","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":86.7,"correct":26,"total":30,"totalCostUsd":1.857498},{"rank":7,"model":"gpt-5.6-sol-high","displayName":"GPT-5.6 Sol (high)","familyDisplayName":"GPT-5.6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-07-09T09:54:10.000Z","family":"gpt-5.6-sol","effort":"high","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":86.7,"correct":26,"total":30,"totalCostUsd":2.270558},{"rank":7,"model":"gpt-6-astra-low","displayName":"GPT-6 Astra (low)","familyDisplayName":"GPT-6 Astra","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-04T20:13:58.000Z","family":"gpt-6-astra","effort":"low","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":86.7,"correct":26,"total":30,"totalCostUsd":3.34609},{"rank":7,"model":"gpt-5.6-sol-xhigh","displayName":"GPT-5.6 Sol (xhigh)","familyDisplayName":"GPT-5.6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-07-09T09:54:10.000Z","family":"gpt-5.6-sol","effort":"xhigh","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":86.7,"correct":26,"total":30,"totalCostUsd":3.776968},{"rank":7,"model":"gpt-5.6-sol-max","displayName":"GPT-5.6 Sol (max)","familyDisplayName":"GPT-5.6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-07-09T09:54:10.000Z","family":"gpt-5.6-sol","effort":"max","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":86.7,"correct":26,"total":30,"totalCostUsd":4.511858},{"rank":7,"model":"claude-opus-5.5-max","displayName":"Claude Opus 5.5 (max)","familyDisplayName":"Claude Opus 5.5","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-22T16:32:12.000Z","family":"claude-opus-5.5","effort":"max","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":86.7,"correct":26,"total":30,"totalCostUsd":8.725936},{"rank":13,"model":"gpt-5.6-sol-medium","displayName":"GPT-5.6 Sol (medium)","familyDisplayName":"GPT-5.6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-07-09T09:54:10.000Z","family":"gpt-5.6-sol","effort":"medium","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":83.3,"correct":25,"total":30,"totalCostUsd":1.394688},{"rank":13,"model":"gemini-3.8-flash-high","displayName":"Gemini 3.8 Flash (high)","familyDisplayName":"Gemini 3.8 Flash","providerName":"Google","openWeights":false,"addedAt":"2026-09-02T15:14:16.000Z","family":"gemini-3.8-flash","effort":"high","provider":"google","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":83.3,"correct":25,"total":30,"totalCostUsd":2.469751},{"rank":13,"model":"deepseek-v4-pro-high","displayName":"DeepSeek V4 Pro (high)","familyDisplayName":"DeepSeek V4 Pro","providerName":"DeepSeek","openWeights":true,"addedAt":"2026-08-12T15:42:44.000Z","family":"deepseek-v4-pro","effort":"high","provider":"deepseek","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":83.3,"correct":25,"total":30,"totalCostUsd":2.73768},{"rank":13,"model":"gpt-6-sol-max","displayName":"GPT-6 Sol (max)","familyDisplayName":"GPT-6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:12:55.000Z","family":"gpt-6-sol","effort":"max","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":83.3,"correct":25,"total":30,"totalCostUsd":3.223972},{"rank":13,"model":"claude-opus-5.5-xhigh","displayName":"Claude Opus 5.5 (xhigh)","familyDisplayName":"Claude Opus 5.5","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-22T16:32:12.000Z","family":"claude-opus-5.5","effort":"xhigh","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":83.3,"correct":25,"total":30,"totalCostUsd":6.742556},{"rank":13,"model":"grok-4.7-high","displayName":"Grok 4.7 (high)","familyDisplayName":"Grok 4.7","providerName":"xAI","openWeights":false,"addedAt":"2026-09-21T16:19:01.000Z","family":"grok-4.7","effort":"high","provider":"x-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":83.3,"correct":25,"total":30,"totalCostUsd":8.973861},{"rank":19,"model":"gpt-6-sol-xhigh","displayName":"GPT-6 Sol (xhigh)","familyDisplayName":"GPT-6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:12:55.000Z","family":"gpt-6-sol","effort":"xhigh","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":80,"correct":24,"total":30,"totalCostUsd":2.420388},{"rank":19,"model":"deepseek-v4-pro-max","displayName":"DeepSeek V4 Pro (max)","familyDisplayName":"DeepSeek V4 Pro","providerName":"DeepSeek","openWeights":true,"addedAt":"2026-08-12T15:42:44.000Z","family":"deepseek-v4-pro","effort":"max","provider":"deepseek","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":80,"correct":24,"total":30,"totalCostUsd":2.562781},{"rank":19,"model":"grok-4.7-low","displayName":"Grok 4.7 (low)","familyDisplayName":"Grok 4.7","providerName":"xAI","openWeights":false,"addedAt":"2026-09-21T16:19:01.000Z","family":"grok-4.7","effort":"low","provider":"x-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":80,"correct":24,"total":30,"totalCostUsd":4.207174},{"rank":22,"model":"deepseek-v4.1-flash-high","displayName":"DeepSeek V4.1 Flash (high)","familyDisplayName":"DeepSeek V4.1 Flash","providerName":"DeepSeek","openWeights":true,"addedAt":"2026-09-10T06:21:25.000Z","family":"deepseek-v4.1-flash","effort":"high","provider":"deepseek","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":0.837644},{"rank":22,"model":"deepseek-v4.1-flash-max","displayName":"DeepSeek V4.1 Flash (max)","familyDisplayName":"DeepSeek V4.1 Flash","providerName":"DeepSeek","openWeights":true,"addedAt":"2026-09-10T06:21:25.000Z","family":"deepseek-v4.1-flash","effort":"max","provider":"deepseek","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":0.839554},{"rank":22,"model":"muse-spark-1.3-xhigh","displayName":"Muse Spark 1.3 (xhigh)","familyDisplayName":"Muse Spark 1.3","providerName":"Meta","openWeights":false,"addedAt":"2026-09-02T19:45:59.000Z","family":"muse-spark-1.3","effort":"xhigh","provider":"meta","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":3.401422},{"rank":22,"model":"gemini-3.1-pro-preview-high","displayName":"Gemini 3.1 Pro Preview (high)","familyDisplayName":"Gemini 3.1 Pro Preview","providerName":"Google","openWeights":false,"addedAt":"2026-02-19T14:00:27.000Z","family":"gemini-3.1-pro-preview","effort":"high","provider":"google","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":5.429724},{"rank":22,"model":"grok-4.7-medium","displayName":"Grok 4.7 (medium)","familyDisplayName":"Grok 4.7","providerName":"xAI","openWeights":false,"addedAt":"2026-09-21T16:19:01.000Z","family":"grok-4.7","effort":"medium","provider":"x-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":6.800694},{"rank":22,"model":"grok-4.7-xhigh","displayName":"Grok 4.7 (xhigh)","familyDisplayName":"Grok 4.7","providerName":"xAI","openWeights":false,"addedAt":"2026-09-21T16:19:01.000Z","family":"grok-4.7","effort":"xhigh","provider":"x-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":9.663472},{"rank":22,"model":"gpt-5.4-xhigh","displayName":"GPT-5.4 (xhigh)","familyDisplayName":"GPT-5.4","providerName":"OpenAI","openWeights":false,"addedAt":"2026-03-05T18:12:32.000Z","family":"gpt-5.4","effort":"xhigh","provider":"openai","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":10.202575},{"rank":22,"model":"kimi-k3-max","displayName":"Kimi K3 (max)","familyDisplayName":"Kimi K3","providerName":"Moonshot AI","openWeights":true,"addedAt":"2026-07-16T15:30:58.000Z","family":"kimi-k3","effort":"max","provider":"moonshotai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":14.521332},{"rank":22,"model":"claude-fable-5.1-xhigh","displayName":"Claude Fable 5.1 (xhigh)","familyDisplayName":"Claude Fable 5.1","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-01T18:03:58.000Z","family":"claude-fable-5.1","effort":"xhigh","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":16.95504},{"rank":22,"model":"claude-fable-5.1-max","displayName":"Claude Fable 5.1 (max)","familyDisplayName":"Claude Fable 5.1","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-01T18:03:58.000Z","family":"claude-fable-5.1","effort":"max","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":76.7,"correct":23,"total":30,"totalCostUsd":20.42329},{"rank":32,"model":"deepseek-v4.1-flash-low","displayName":"DeepSeek V4.1 Flash (low)","familyDisplayName":"DeepSeek V4.1 Flash","providerName":"DeepSeek","openWeights":true,"addedAt":"2026-09-10T06:21:25.000Z","family":"deepseek-v4.1-flash","effort":"low","provider":"deepseek","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":73.3,"correct":22,"total":30,"totalCostUsd":0.616501},{"rank":32,"model":"muse-spark-1.3-max","displayName":"Muse Spark 1.3 (max)","familyDisplayName":"Muse Spark 1.3","providerName":"Meta","openWeights":false,"addedAt":"2026-09-02T19:45:59.000Z","family":"muse-spark-1.3","effort":"max","provider":"meta","earlierBatch":false,"version":"1.2","complete":false,"providerTimeouts":1,"providerTimeoutNote":"Meta's API ends requests after about 5 minutes, before the model answered: Network connection lost.","reasoning":true,"accuracy":73.3,"correct":22,"total":30,"totalCostUsd":2.882096},{"rank":34,"model":"muse-spark-1.3-high","displayName":"Muse Spark 1.3 (high)","familyDisplayName":"Muse Spark 1.3","providerName":"Meta","openWeights":false,"addedAt":"2026-09-02T19:45:59.000Z","family":"muse-spark-1.3","effort":"high","provider":"meta","earlierBatch":false,"version":"1.2","complete":false,"providerTimeouts":9,"providerTimeoutNote":"Meta's API ends requests after about 5 minutes, before the model answered: Network connection lost.","reasoning":true,"accuracy":70,"correct":21,"total":30,"totalCostUsd":0.975151},{"rank":34,"model":"muse-spark-1.3-low","displayName":"Muse Spark 1.3 (low)","familyDisplayName":"Muse Spark 1.3","providerName":"Meta","openWeights":false,"addedAt":"2026-09-02T19:45:59.000Z","family":"muse-spark-1.3","effort":"low","provider":"meta","earlierBatch":false,"version":"1.2","complete":false,"providerTimeouts":4,"providerTimeoutNote":"Meta's API ends requests after about 5 minutes, before the model answered","reasoning":true,"accuracy":70,"correct":21,"total":30,"totalCostUsd":1.204475},{"rank":34,"model":"gpt-6-sol-medium","displayName":"GPT-6 Sol (medium)","familyDisplayName":"GPT-6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:12:55.000Z","family":"gpt-6-sol","effort":"medium","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":70,"correct":21,"total":30,"totalCostUsd":1.239598},{"rank":34,"model":"deepseek-v4-pro-low","displayName":"DeepSeek V4 Pro (low)","familyDisplayName":"DeepSeek V4 Pro","providerName":"DeepSeek","openWeights":true,"addedAt":"2026-08-12T15:42:44.000Z","family":"deepseek-v4-pro","effort":"low","provider":"deepseek","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":70,"correct":21,"total":30,"totalCostUsd":1.655294},{"rank":38,"model":"qwen3.8-flash","displayName":"Qwen3.8 Flash (reasoning)","familyDisplayName":"Qwen3.8 Flash","providerName":"Qwen","openWeights":true,"addedAt":"2026-08-26T19:37:40.000Z","family":"qwen3.8-flash","effort":"default","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":66.7,"correct":20,"total":30,"totalCostUsd":0.732024},{"rank":38,"model":"muse-spark-1.3-medium","displayName":"Muse Spark 1.3 (medium)","familyDisplayName":"Muse Spark 1.3","providerName":"Meta","openWeights":false,"addedAt":"2026-09-02T19:45:59.000Z","family":"muse-spark-1.3","effort":"medium","provider":"meta","earlierBatch":false,"version":"1.2","complete":false,"providerTimeouts":8,"providerTimeoutNote":"Meta's API ends requests after about 5 minutes, before the model answered","reasoning":true,"accuracy":66.7,"correct":20,"total":30,"totalCostUsd":0.91038},{"rank":38,"model":"gemini-3.8-flash-medium","displayName":"Gemini 3.8 Flash (medium)","familyDisplayName":"Gemini 3.8 Flash","providerName":"Google","openWeights":false,"addedAt":"2026-09-02T15:14:16.000Z","family":"gemini-3.8-flash","effort":"medium","provider":"google","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":66.7,"correct":20,"total":30,"totalCostUsd":1.306393},{"rank":38,"model":"gpt-5.4-high","displayName":"GPT-5.4 (high)","familyDisplayName":"GPT-5.4","providerName":"OpenAI","openWeights":false,"addedAt":"2026-03-05T18:12:32.000Z","family":"gpt-5.4","effort":"high","provider":"openai","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":66.7,"correct":20,"total":30,"totalCostUsd":8.63071},{"rank":38,"model":"gpt-5.2-high","displayName":"GPT-5.2 (high)","familyDisplayName":"GPT-5.2","providerName":"OpenAI","openWeights":false,"addedAt":"2025-12-10T18:02:55.000Z","family":"gpt-5.2","effort":"high","provider":"openai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":66.7,"correct":20,"total":30,"totalCostUsd":10.856275},{"rank":38,"model":"claude-fable-5.1-high","displayName":"Claude Fable 5.1 (high)","familyDisplayName":"Claude Fable 5.1","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-01T18:03:58.000Z","family":"claude-fable-5.1","effort":"high","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":66.7,"correct":20,"total":30,"totalCostUsd":15.18989},{"rank":44,"model":"kimi-k3-high","displayName":"Kimi K3 (high)","familyDisplayName":"Kimi K3","providerName":"Moonshot AI","openWeights":true,"addedAt":"2026-07-16T15:30:58.000Z","family":"kimi-k3","effort":"high","provider":"moonshotai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":63.3,"correct":19,"total":30,"totalCostUsd":8.842167},{"rank":45,"model":"kimi-k3-low","displayName":"Kimi K3 (low)","familyDisplayName":"Kimi K3","providerName":"Moonshot AI","openWeights":true,"addedAt":"2026-07-16T15:30:58.000Z","family":"kimi-k3","effort":"low","provider":"moonshotai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":60,"correct":18,"total":30,"totalCostUsd":3.307947},{"rank":45,"model":"claude-opus-5.5-low","displayName":"Claude Opus 5.5 (low)","familyDisplayName":"Claude Opus 5.5","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-22T16:32:12.000Z","family":"claude-opus-5.5","effort":"low","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":60,"correct":18,"total":30,"totalCostUsd":3.450016},{"rank":45,"model":"qwen3.8-max-minimal","displayName":"Qwen3.8 Max (minimal)","familyDisplayName":"Qwen3.8 Max","providerName":"Qwen","openWeights":false,"addedAt":"2026-09-03T21:08:24.000Z","family":"qwen3.8-max","effort":"minimal","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":60,"correct":18,"total":30,"totalCostUsd":4.815102},{"rank":45,"model":"qwen3.8-max-low","displayName":"Qwen3.8 Max (low)","familyDisplayName":"Qwen3.8 Max","providerName":"Qwen","openWeights":false,"addedAt":"2026-09-03T21:08:24.000Z","family":"qwen3.8-max","effort":"low","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":60,"correct":18,"total":30,"totalCostUsd":4.991418},{"rank":45,"model":"qwen3.8-max-high","displayName":"Qwen3.8 Max (high)","familyDisplayName":"Qwen3.8 Max","providerName":"Qwen","openWeights":false,"addedAt":"2026-09-03T21:08:24.000Z","family":"qwen3.8-max","effort":"high","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":60,"correct":18,"total":30,"totalCostUsd":5.47236},{"rank":45,"model":"qwen3.8-max-xhigh","displayName":"Qwen3.8 Max (xhigh)","familyDisplayName":"Qwen3.8 Max","providerName":"Qwen","openWeights":false,"addedAt":"2026-09-03T21:08:24.000Z","family":"qwen3.8-max","effort":"xhigh","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":60,"correct":18,"total":30,"totalCostUsd":5.840052},{"rank":45,"model":"claude-fable-5.1-medium","displayName":"Claude Fable 5.1 (medium)","familyDisplayName":"Claude Fable 5.1","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-01T18:03:58.000Z","family":"claude-fable-5.1","effort":"medium","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":60,"correct":18,"total":30,"totalCostUsd":14.94059},{"rank":45,"model":"claude-4.5-opus-high","displayName":"Claude Opus 4.5 (high)","familyDisplayName":"Claude Opus 4.5","providerName":"Anthropic","openWeights":false,"addedAt":"2025-11-24T18:56:20.000Z","family":"claude-4.5-opus","effort":"high","provider":"anthropic","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":60,"correct":18,"total":30,"totalCostUsd":23.08302},{"rank":53,"model":"gpt-6-sol-low","displayName":"GPT-6 Sol (low)","familyDisplayName":"GPT-6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:12:55.000Z","family":"gpt-6-sol","effort":"low","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":56.7,"correct":17,"total":30,"totalCostUsd":0.450078},{"rank":53,"model":"gemini-3-pro-preview-high","displayName":"Gemini 3 Pro Preview (high)","familyDisplayName":"Gemini 3 Pro Preview","providerName":"Google","openWeights":null,"addedAt":null,"family":"gemini-3-pro-preview","effort":"high","provider":"google","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":56.7,"correct":17,"total":30,"totalCostUsd":5.196098},{"rank":53,"model":"gpt-5.2-xhigh","displayName":"GPT-5.2 (xhigh)","familyDisplayName":"GPT-5.2","providerName":"OpenAI","openWeights":false,"addedAt":"2025-12-10T18:02:55.000Z","family":"gpt-5.2","effort":"xhigh","provider":"openai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":56.7,"correct":17,"total":30,"totalCostUsd":12.410076},{"rank":56,"model":"seed-2.1-turbo","displayName":"Seed 2.1 Turbo (reasoning)","familyDisplayName":"Seed 2.1 Turbo","providerName":"ByteDance Seed","openWeights":false,"addedAt":"2026-08-12T16:29:36.000Z","family":"seed-2.1-turbo","effort":"default","provider":"bytedance-seed","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":53.3,"correct":16,"total":30,"totalCostUsd":3.12876},{"rank":57,"model":"gpt-6-luna-max","displayName":"GPT-6 Luna (max)","familyDisplayName":"GPT-6 Luna","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:13:06.000Z","family":"gpt-6-luna","effort":"max","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":50,"correct":15,"total":30,"totalCostUsd":0.386755},{"rank":57,"model":"gpt-5.6-sol-low","displayName":"GPT-5.6 Sol (low)","familyDisplayName":"GPT-5.6 Sol","providerName":"OpenAI","openWeights":false,"addedAt":"2026-07-09T09:54:10.000Z","family":"gpt-5.6-sol","effort":"low","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":50,"correct":15,"total":30,"totalCostUsd":0.697318},{"rank":57,"model":"muse-spark-1.3-minimal","displayName":"Muse Spark 1.3 (minimal)","familyDisplayName":"Muse Spark 1.3","providerName":"Meta","openWeights":false,"addedAt":"2026-09-02T19:45:59.000Z","family":"muse-spark-1.3","effort":"minimal","provider":"meta","earlierBatch":false,"version":"1.2","complete":false,"providerTimeouts":2,"providerTimeoutNote":"Meta's API ends requests after about 5 minutes, before the model answered: Network connection lost.","reasoning":true,"accuracy":50,"correct":15,"total":30,"totalCostUsd":1.14124},{"rank":57,"model":"gemini-3-flash-preview-high","displayName":"Gemini 3 Flash Preview (high)","familyDisplayName":"Gemini 3 Flash Preview","providerName":"Google","openWeights":false,"addedAt":"2025-12-17T15:57:58.000Z","family":"gemini-3-flash-preview","effort":"high","provider":"google","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":50,"correct":15,"total":30,"totalCostUsd":1.682046},{"rank":57,"model":"gpt-5.4-low","displayName":"GPT-5.4 (low)","familyDisplayName":"GPT-5.4","providerName":"OpenAI","openWeights":false,"addedAt":"2026-03-05T18:12:32.000Z","family":"gpt-5.4","effort":"low","provider":"openai","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":50,"correct":15,"total":30,"totalCostUsd":3.203395},{"rank":57,"model":"gpt-5.2-low","displayName":"GPT-5.2 (low)","familyDisplayName":"GPT-5.2","providerName":"OpenAI","openWeights":false,"addedAt":"2025-12-10T18:02:55.000Z","family":"gpt-5.2","effort":"low","provider":"openai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":50,"correct":15,"total":30,"totalCostUsd":3.986616},{"rank":57,"model":"claude-4.5-opus-low","displayName":"Claude Opus 4.5 (low)","familyDisplayName":"Claude Opus 4.5","providerName":"Anthropic","openWeights":false,"addedAt":"2025-11-24T18:56:20.000Z","family":"claude-4.5-opus","effort":"low","provider":"anthropic","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":50,"correct":15,"total":30,"totalCostUsd":6.45372},{"rank":57,"model":"claude-fable-5.1-low","displayName":"Claude Fable 5.1 (low)","familyDisplayName":"Claude Fable 5.1","providerName":"Anthropic","openWeights":false,"addedAt":"2026-09-01T18:03:58.000Z","family":"claude-fable-5.1","effort":"low","provider":"anthropic","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":50,"correct":15,"total":30,"totalCostUsd":14.79969},{"rank":65,"model":"gpt-6-luna-xhigh","displayName":"GPT-6 Luna (xhigh)","familyDisplayName":"GPT-6 Luna","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:13:06.000Z","family":"gpt-6-luna","effort":"xhigh","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":46.7,"correct":14,"total":30,"totalCostUsd":0.301558},{"rank":65,"model":"deepseek-v3.2-speciale-high","displayName":"DeepSeek V3.2 Speciale (high)","familyDisplayName":"DeepSeek V3.2 Speciale","providerName":"DeepSeek","openWeights":true,"addedAt":null,"family":"deepseek-v3.2-speciale","effort":"high","provider":"deepseek","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":46.7,"correct":14,"total":30,"totalCostUsd":0.437673},{"rank":65,"model":"mimo-v2.6-pro","displayName":"MiMo V2.6 Pro (reasoning)","familyDisplayName":"MiMo V2.6 Pro","providerName":"Xiaomi","openWeights":true,"addedAt":"2026-09-21T20:07:39.000Z","family":"mimo-v2.6-pro","effort":"default","provider":"xiaomi","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":46.7,"correct":14,"total":30,"totalCostUsd":1.001973},{"rank":65,"model":"qwen3.8-27b-xhigh","displayName":"Qwen3.8 27B (xhigh)","familyDisplayName":"Qwen3.8 27B","providerName":"Qwen","openWeights":true,"addedAt":"2026-08-14T15:55:10.000Z","family":"qwen3.8-27b","effort":"xhigh","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":46.7,"correct":14,"total":30,"totalCostUsd":3.606911},{"rank":65,"model":"qwen3.8-max-medium","displayName":"Qwen3.8 Max (medium)","familyDisplayName":"Qwen3.8 Max","providerName":"Qwen","openWeights":false,"addedAt":"2026-09-03T21:08:24.000Z","family":"qwen3.8-max","effort":"medium","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":46.7,"correct":14,"total":30,"totalCostUsd":4.884822},{"rank":70,"model":"gpt-oss-120b-high","displayName":"gpt-oss-120b (high)","familyDisplayName":"gpt-oss-120b","providerName":"OpenAI","openWeights":true,"addedAt":"2025-08-05T17:17:11.000Z","family":"gpt-oss-120b","effort":"high","provider":"openai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":43.3,"correct":13,"total":30,"totalCostUsd":0.24782},{"rank":70,"model":"deepseek-v3.2-high","displayName":"DeepSeek V3.2 (high)","familyDisplayName":"DeepSeek V3.2","providerName":"DeepSeek","openWeights":true,"addedAt":"2025-12-01T13:10:42.000Z","family":"deepseek-v3.2","effort":"high","provider":"deepseek","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":43.3,"correct":13,"total":30,"totalCostUsd":0.616697},{"rank":70,"model":"gemini-3.1-pro-preview-low","displayName":"Gemini 3.1 Pro Preview (low)","familyDisplayName":"Gemini 3.1 Pro Preview","providerName":"Google","openWeights":false,"addedAt":"2026-02-19T14:00:27.000Z","family":"gemini-3.1-pro-preview","effort":"low","provider":"google","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":43.3,"correct":13,"total":30,"totalCostUsd":0.876596},{"rank":70,"model":"kimi-k2.5-high","displayName":"Kimi K2.5 (high)","familyDisplayName":"Kimi K2.5","providerName":"Moonshot AI","openWeights":true,"addedAt":"2026-01-27T04:11:16.000Z","family":"kimi-k2.5","effort":"high","provider":"moonshotai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":43.3,"correct":13,"total":30,"totalCostUsd":2.557349},{"rank":74,"model":"deepseek-v3.2-speciale","displayName":"DeepSeek V3.2 Speciale (no reasoning)","familyDisplayName":"DeepSeek V3.2 Speciale","providerName":"DeepSeek","openWeights":true,"addedAt":null,"family":"deepseek-v3.2-speciale","effort":"none","provider":"deepseek","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":40,"correct":12,"total":30,"totalCostUsd":0.391333},{"rank":74,"model":"glm-5.3-flash-max","displayName":"GLM 5.3 Flash (max)","familyDisplayName":"GLM 5.3 Flash","providerName":"Z.ai","openWeights":true,"addedAt":"2026-08-26T13:59:01.000Z","family":"glm-5.3-flash","effort":"max","provider":"z-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":40,"correct":12,"total":30,"totalCostUsd":0.664714},{"rank":76,"model":"gemini-3.8-flash-low","displayName":"Gemini 3.8 Flash (low)","familyDisplayName":"Gemini 3.8 Flash","providerName":"Google","openWeights":false,"addedAt":"2026-09-02T15:14:16.000Z","family":"gemini-3.8-flash","effort":"low","provider":"google","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":36.7,"correct":11,"total":30,"totalCostUsd":0.216413},{"rank":76,"model":"glm-5.3-max","displayName":"GLM 5.3 (max)","familyDisplayName":"GLM 5.3","providerName":"Z.ai","openWeights":true,"addedAt":"2026-08-18T20:57:35.000Z","family":"glm-5.3","effort":"max","provider":"z-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":36.7,"correct":11,"total":30,"totalCostUsd":4.723258},{"rank":78,"model":"gpt-oss-120b-low","displayName":"gpt-oss-120b (low)","familyDisplayName":"gpt-oss-120b","providerName":"OpenAI","openWeights":true,"addedAt":"2025-08-05T17:17:11.000Z","family":"gpt-oss-120b","effort":"low","provider":"openai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":0.028993},{"rank":78,"model":"gpt-6-luna-high","displayName":"GPT-6 Luna (high)","familyDisplayName":"GPT-6 Luna","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:13:06.000Z","family":"gpt-6-luna","effort":"high","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":0.216022},{"rank":78,"model":"mimo-v2.6-flash","displayName":"MiMo V2.6 Flash (reasoning)","familyDisplayName":"MiMo V2.6 Flash","providerName":"Xiaomi","openWeights":true,"addedAt":"2026-09-21T20:07:44.000Z","family":"mimo-v2.6-flash","effort":"default","provider":"xiaomi","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":0.384161},{"rank":78,"model":"seed-1.6-high","displayName":"Seed 1.6 (high)","familyDisplayName":"Seed 1.6","providerName":"ByteDance Seed","openWeights":false,"addedAt":"2025-12-23T15:49:57.000Z","family":"seed-1.6","effort":"high","provider":"bytedance-seed","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":0.82632},{"rank":78,"model":"qwen3.8-27b-medium","displayName":"Qwen3.8 27B (medium)","familyDisplayName":"Qwen3.8 27B","providerName":"Qwen","openWeights":true,"addedAt":"2026-08-14T15:55:10.000Z","family":"qwen3.8-27b","effort":"medium","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":0.906426},{"rank":78,"model":"qwen3-next-80b-a3b-thinking","displayName":"Qwen3 Next 80B A3B Thinking (reasoning)","familyDisplayName":"Qwen3 Next 80B A3B Thinking","providerName":"Qwen","openWeights":true,"addedAt":"2025-09-11T17:38:04.000Z","family":"qwen3-next-80b-a3b-thinking","effort":"default","provider":"qwen","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":0.9311},{"rank":78,"model":"minimax-m2.5-high","displayName":"MiniMax M2.5 (high)","familyDisplayName":"MiniMax M2.5","providerName":"MiniMax","openWeights":true,"addedAt":"2026-02-12T15:01:42.000Z","family":"minimax-m2.5","effort":"high","provider":"minimax","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":1.49441},{"rank":78,"model":"glm-5.3-low","displayName":"GLM 5.3 (low)","familyDisplayName":"GLM 5.3","providerName":"Z.ai","openWeights":true,"addedAt":"2026-08-18T20:57:35.000Z","family":"glm-5.3","effort":"low","provider":"z-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":3.906944},{"rank":78,"model":"grok-4","displayName":"Grok 4 (reasoning)","familyDisplayName":"Grok 4","providerName":"xAI","openWeights":null,"addedAt":null,"family":"grok-4","effort":"default","provider":"x-ai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":33.3,"correct":10,"total":30,"totalCostUsd":15.060292},{"rank":87,"model":"gpt-6-luna-medium","displayName":"GPT-6 Luna (medium)","familyDisplayName":"GPT-6 Luna","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:13:06.000Z","family":"gpt-6-luna","effort":"medium","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":30,"correct":9,"total":30,"totalCostUsd":0.110878},{"rank":87,"model":"minimax-m2.1-high","displayName":"MiniMax M2.1 (high)","familyDisplayName":"MiniMax M2.1","providerName":"MiniMax","openWeights":true,"addedAt":"2025-12-23T01:56:37.000Z","family":"minimax-m2.1","effort":"high","provider":"minimax","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":30,"correct":9,"total":30,"totalCostUsd":0.61319},{"rank":87,"model":"glm-5.3-flash-high","displayName":"GLM 5.3 Flash (high)","familyDisplayName":"GLM 5.3 Flash","providerName":"Z.ai","openWeights":true,"addedAt":"2026-08-26T13:59:01.000Z","family":"glm-5.3-flash","effort":"high","provider":"z-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":30,"correct":9,"total":30,"totalCostUsd":0.683762},{"rank":87,"model":"glm-5-reasoning-high","displayName":"GLM 5 (high)","familyDisplayName":"GLM 5","providerName":"Z.ai","openWeights":true,"addedAt":"2026-02-11T16:59:42.000Z","family":"glm-5","effort":"high","provider":"z-ai","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":30,"correct":9,"total":30,"totalCostUsd":1.523257},{"rank":87,"model":"claude-4.5-sonnet-reasoning","displayName":"Claude Sonnet 4.5 (reasoning)","familyDisplayName":"Claude Sonnet 4.5","providerName":"Anthropic","openWeights":false,"addedAt":"2025-09-29T16:01:16.000Z","family":"claude-4.5-sonnet","effort":"default","provider":"anthropic","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":30,"correct":9,"total":30,"totalCostUsd":5.97906},{"rank":87,"model":"mistral-medium-3.5-low","displayName":"Mistral Medium 3.5 (low)","familyDisplayName":"Mistral Medium 3.5","providerName":"Mistral AI","openWeights":false,"addedAt":"2026-04-30T17:33:59.000Z","family":"mistral-medium-3.5","effort":"low","provider":"mistralai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":30,"correct":9,"total":30,"totalCostUsd":7.141446},{"rank":87,"model":"mistral-medium-3.5-high","displayName":"Mistral Medium 3.5 (high)","familyDisplayName":"Mistral Medium 3.5","providerName":"Mistral AI","openWeights":false,"addedAt":"2026-04-30T17:33:59.000Z","family":"mistral-medium-3.5","effort":"high","provider":"mistralai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":30,"correct":9,"total":30,"totalCostUsd":7.583188},{"rank":94,"model":"minimax-m2.5","displayName":"MiniMax M2.5 (reasoning)","familyDisplayName":"MiniMax M2.5","providerName":"MiniMax","openWeights":true,"addedAt":"2026-02-12T15:01:42.000Z","family":"minimax-m2.5","effort":"default","provider":"minimax","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":26.7,"correct":8,"total":30,"totalCostUsd":1.652709},{"rank":94,"model":"kimi-k2-thinking","displayName":"Kimi K2 Thinking (reasoning)","familyDisplayName":"Kimi K2 Thinking","providerName":"Moonshot AI","openWeights":true,"addedAt":"2025-11-06T14:50:22.000Z","family":"kimi-k2-thinking","effort":"default","provider":"moonshotai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":26.7,"correct":8,"total":30,"totalCostUsd":2.983311},{"rank":96,"model":"gpt-6-luna-low","displayName":"GPT-6 Luna (low)","familyDisplayName":"GPT-6 Luna","providerName":"OpenAI","openWeights":false,"addedAt":"2026-09-22T18:13:06.000Z","family":"gpt-6-luna","effort":"low","provider":"openai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":23.3,"correct":7,"total":30,"totalCostUsd":0.021396},{"rank":96,"model":"qwen3.8-27b-low","displayName":"Qwen3.8 27B (low)","familyDisplayName":"Qwen3.8 27B","providerName":"Qwen","openWeights":true,"addedAt":"2026-08-14T15:55:10.000Z","family":"qwen3.8-27b","effort":"low","provider":"qwen","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":23.3,"correct":7,"total":30,"totalCostUsd":0.438982},{"rank":96,"model":"grok-4.1-fast-reasoning","displayName":"Grok 4.1 Fast (reasoning)","familyDisplayName":"Grok 4.1 Fast","providerName":"xAI","openWeights":null,"addedAt":null,"family":"grok-4.1-fast","effort":"default","provider":"x-ai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":23.3,"correct":7,"total":30,"totalCostUsd":0.48476},{"rank":96,"model":"glm-5.3-flash-low","displayName":"GLM 5.3 Flash (low)","familyDisplayName":"GLM 5.3 Flash","providerName":"Z.ai","openWeights":true,"addedAt":"2026-08-26T13:59:01.000Z","family":"glm-5.3-flash","effort":"low","provider":"z-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":23.3,"correct":7,"total":30,"totalCostUsd":0.621846},{"rank":96,"model":"glm-5-reasoning","displayName":"GLM 5 (reasoning)","familyDisplayName":"GLM 5","providerName":"Z.ai","openWeights":true,"addedAt":"2026-02-11T16:59:42.000Z","family":"glm-5","effort":"default","provider":"z-ai","earlierBatch":true,"version":"1.1","complete":true,"reasoning":true,"accuracy":23.3,"correct":7,"total":30,"totalCostUsd":1.920909},{"rank":101,"model":"mimo-v2-flash-high","displayName":"MiMo V2 Flash (high)","familyDisplayName":"MiMo V2 Flash","providerName":"Xiaomi","openWeights":true,"addedAt":null,"family":"mimo-v2-flash","effort":"high","provider":"xiaomi","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":20,"correct":6,"total":30,"totalCostUsd":0},{"rank":101,"model":"minimax-m2.1","displayName":"MiniMax M2.1 (reasoning)","familyDisplayName":"MiniMax M2.1","providerName":"MiniMax","openWeights":true,"addedAt":"2025-12-23T01:56:37.000Z","family":"minimax-m2.1","effort":"default","provider":"minimax","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":20,"correct":6,"total":30,"totalCostUsd":0.569036},{"rank":101,"model":"glm-4.7-reasoning","displayName":"GLM 4.7 (reasoning)","familyDisplayName":"GLM 4.7","providerName":"Z.ai","openWeights":true,"addedAt":"2025-12-22T04:33:34.000Z","family":"glm-4.7","effort":"default","provider":"z-ai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":20,"correct":6,"total":30,"totalCostUsd":1.130683},{"rank":101,"model":"glm-5.3-high","displayName":"GLM 5.3 (high)","familyDisplayName":"GLM 5.3","providerName":"Z.ai","openWeights":true,"addedAt":"2026-08-18T20:57:35.000Z","family":"glm-5.3","effort":"high","provider":"z-ai","earlierBatch":false,"version":"1.2","complete":true,"reasoning":true,"accuracy":20,"correct":6,"total":30,"totalCostUsd":4.781945},{"rank":105,"model":"seed-1.6-flash-high","displayName":"Seed 1.6 Flash (high)","familyDisplayName":"Seed 1.6 Flash","providerName":"ByteDance Seed","openWeights":false,"addedAt":"2025-12-23T15:50:11.000Z","family":"seed-1.6-flash","effort":"high","provider":"bytedance-seed","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":13.3,"correct":4,"total":30,"totalCostUsd":0.201528},{"rank":105,"model":"olmo-3.1-32b-think","displayName":"OLMo 3.1 32B Think (reasoning)","familyDisplayName":"OLMo 3.1 32B Think","providerName":"Allen Institute for AI","openWeights":true,"addedAt":null,"family":"olmo-3.1-32b-think","effort":"default","provider":"allenai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":13.3,"correct":4,"total":30,"totalCostUsd":0.33989},{"rank":105,"model":"grok-4.1-fast-reasoning-high","displayName":"Grok 4.1 Fast (high)","familyDisplayName":"Grok 4.1 Fast","providerName":"xAI","openWeights":null,"addedAt":null,"family":"grok-4.1-fast","effort":"high","provider":"x-ai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":13.3,"correct":4,"total":30,"totalCostUsd":0.432766},{"rank":105,"model":"glm-4.7-reasoning-high","displayName":"GLM 4.7 (high)","familyDisplayName":"GLM 4.7","providerName":"Z.ai","openWeights":true,"addedAt":"2025-12-22T04:33:34.000Z","family":"glm-4.7","effort":"high","provider":"z-ai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":13.3,"correct":4,"total":30,"totalCostUsd":1.156024},{"rank":109,"model":"deepseek-v3.2","displayName":"DeepSeek V3.2 (no reasoning)","familyDisplayName":"DeepSeek V3.2","providerName":"DeepSeek","openWeights":true,"addedAt":"2025-12-01T13:10:42.000Z","family":"deepseek-v3.2","effort":"none","provider":"deepseek","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":6.7,"correct":2,"total":30,"totalCostUsd":0.040991},{"rank":109,"model":"kimi-k2","displayName":"Kimi K2 (no reasoning)","familyDisplayName":"Kimi K2","providerName":"Moonshot AI","openWeights":true,"addedAt":"2025-09-04T21:25:47.000Z","family":"kimi-k2","effort":"none","provider":"moonshotai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":6.7,"correct":2,"total":30,"totalCostUsd":0.233484},{"rank":111,"model":"mimo-v2-flash","displayName":"MiMo V2 Flash (no reasoning)","familyDisplayName":"MiMo V2 Flash","providerName":"Xiaomi","openWeights":true,"addedAt":null,"family":"mimo-v2-flash","effort":"none","provider":"xiaomi","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0},{"rank":111,"model":"glm-4.7-non-reasoning","displayName":"GLM 4.7 (no reasoning)","familyDisplayName":"GLM 4.7","providerName":"Z.ai","openWeights":true,"addedAt":"2025-12-22T04:33:34.000Z","family":"glm-4.7","effort":"none","provider":"z-ai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.008812},{"rank":111,"model":"ministral-14b-2512","displayName":"Ministral 3 14B 2512 (no reasoning)","familyDisplayName":"Ministral 3 14B 2512","providerName":"Mistral AI","openWeights":true,"addedAt":"2025-12-02T13:22:15.000Z","family":"ministral-14b-2512","effort":"none","provider":"mistralai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.009936},{"rank":111,"model":"glm-5-non-reasoning","displayName":"GLM 5 (no reasoning)","familyDisplayName":"GLM 5","providerName":"Z.ai","openWeights":true,"addedAt":"2026-02-11T16:59:42.000Z","family":"glm-5","effort":"none","provider":"z-ai","earlierBatch":true,"version":"1.1","complete":true,"reasoning":false,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.012976},{"rank":111,"model":"kimi-k2.5-non-reasoning","displayName":"Kimi K2.5 (no reasoning)","familyDisplayName":"Kimi K2.5","providerName":"Moonshot AI","openWeights":true,"addedAt":"2026-01-27T04:11:16.000Z","family":"kimi-k2.5","effort":"none","provider":"moonshotai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.013433},{"rank":111,"model":"mistral-large-2512","displayName":"Mistral Large 3 2512 (no reasoning)","familyDisplayName":"Mistral Large 3 2512","providerName":"Mistral AI","openWeights":true,"addedAt":"2025-12-01T21:27:52.000Z","family":"mistral-large-2512","effort":"none","provider":"mistralai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.016439},{"rank":111,"model":"gemini-3-flash-preview-minimal","displayName":"Gemini 3 Flash Preview (minimal)","familyDisplayName":"Gemini 3 Flash Preview","providerName":"Google","openWeights":false,"addedAt":"2025-12-17T15:57:58.000Z","family":"gemini-3-flash-preview","effort":"minimal","provider":"google","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.017212},{"rank":111,"model":"grok-4.1-fast-non-reasoning","displayName":"Grok 4.1 Fast (no reasoning)","familyDisplayName":"Grok 4.1 Fast","providerName":"xAI","openWeights":null,"addedAt":null,"family":"grok-4.1-fast","effort":"none","provider":"x-ai","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.076665},{"rank":111,"model":"gemini-3-pro-preview-low","displayName":"Gemini 3 Pro Preview (low)","familyDisplayName":"Gemini 3 Pro Preview","providerName":"Google","openWeights":null,"addedAt":null,"family":"gemini-3-pro-preview","effort":"low","provider":"google","earlierBatch":true,"version":"1.0","complete":true,"reasoning":true,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.120408},{"rank":111,"model":"claude-4.5-sonnet-non-reasoning","displayName":"Claude Sonnet 4.5 (no reasoning)","familyDisplayName":"Claude Sonnet 4.5","providerName":"Anthropic","openWeights":false,"addedAt":"2025-09-29T16:01:16.000Z","family":"claude-4.5-sonnet","effort":"none","provider":"anthropic","earlierBatch":true,"version":"1.0","complete":true,"reasoning":false,"accuracy":0,"correct":0,"total":30,"totalCostUsd":0.333657}]}