{"rows":[{"rank":1,"variantId":88,"modelSlug":"anthropic--claude-opus-4.6","modelName":"Anthropic: Claude Opus 4.6","providerSlug":"anthropic","providerName":"Anthropic","modelFamily":null,"openWeights":false,"overallScore":96.1,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"json":null,"multilingual":94.7,"agentic":52.4,"math":null,"computer_use":null,"writing":null,"eq":null,"long_context":null,"reasoning":null,"uncensored":null,"instruction_following":null,"multimodal":75.8,"coding":70.6,"overall":96.1,"tool_use":76.3,"hallucination":null},"freshness":{"json":null,"multilingual":"2026-06-05T07:22:32+00:00","agentic":"2026-05-14T00:00:00+00:00","math":"2026-07-13T00:00:00+00:00","computer_use":null,"writing":"2026-08-27T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","long_context":null,"reasoning":"2026-07-13T00:00:00+00:00","uncensored":null,"instruction_following":null,"multimodal":"2000-01-01T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","tool_use":"2000-01-01T00:00:00+00:00","hallucination":null},"confidence":{"json":0.0,"multilingual":0.38,"agentic":0.1,"math":0.0,"computer_use":0.0,"writing":0.0,"eq":0.0,"long_context":0.0,"reasoning":0.0,"uncensored":0.0,"instruction_following":0.0,"multimodal":0.22,"coding":0.05,"overall":0.12,"tool_use":0.54,"hallucination":0.0},"sourceCounts":{"json":0,"multilingual":2,"agentic":3,"math":2,"computer_use":0,"writing":2,"eq":2,"long_context":0,"reasoning":4,"uncensored":0,"instruction_following":0,"multimodal":1,"coding":6,"overall":2,"tool_use":1,"hallucination":0},"inputCostPerMillion":5.0,"outputCostPerMillion":25.0,"contextWindowTokens":1000000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multilingual","Multimodal","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":2,"variantId":38,"modelSlug":"anthropic--claude-opus-4.7","modelName":"Anthropic: Claude Opus 4.7","providerSlug":"anthropic","providerName":"Anthropic","modelFamily":null,"openWeights":false,"overallScore":95.6,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"long_context":null,"instruction_following":null,"multilingual":null,"multimodal":75.0,"computer_use":null,"agentic":61.7,"eq":null,"hallucination":null,"uncensored":null,"tool_use":78.6,"coding":70.3,"overall":95.6,"math":null,"writing":null,"json":null,"reasoning":68.3},"freshness":{"long_context":null,"instruction_following":null,"multilingual":"2026-07-28T12:18:16+00:00","multimodal":"2026-05-08T17:00:24.288957+00:00","computer_use":null,"agentic":"2026-05-15T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","hallucination":null,"uncensored":null,"tool_use":"2000-01-01T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","math":"2000-01-01T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","json":null,"reasoning":"2026-05-08T17:00:24.288957+00:00"},"confidence":{"long_context":0.0,"instruction_following":0.0,"multilingual":0.0,"multimodal":0.26,"computer_use":0.0,"agentic":0.1,"eq":0.0,"hallucination":0.0,"uncensored":0.0,"tool_use":0.54,"coding":0.05,"overall":0.21,"math":0.0,"writing":0.0,"json":0.0,"reasoning":0.09},"sourceCounts":{"long_context":0,"instruction_following":0,"multilingual":1,"multimodal":1,"computer_use":0,"agentic":3,"eq":2,"hallucination":0,"uncensored":0,"tool_use":1,"coding":6,"overall":1,"math":1,"writing":1,"json":0,"reasoning":5},"inputCostPerMillion":5.0,"outputCostPerMillion":25.0,"contextWindowTokens":1000000,"medianLatencyMs":null,"outputTokensPerSecond":56.6116217456673,"bestFor":["Multimodal","Overall","Tool Use"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":3,"variantId":25,"modelSlug":"openai--gpt-5.5","modelName":"OpenAI: GPT-5.5","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":91.4,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"tool_use":null,"hallucination":89.7,"agentic":77.7,"long_context":null,"multimodal":81.7,"multilingual":null,"eq":null,"computer_use":null,"uncensored":54.3,"instruction_following":null,"writing":89.9,"coding":null,"reasoning":74.0,"json":null,"math":null,"overall":91.4},"freshness":{"tool_use":null,"hallucination":"2000-01-01T00:00:00+00:00","agentic":"2026-06-23T00:00:00+00:00","long_context":null,"multimodal":"2000-01-01T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","eq":"2000-01-01T00:00:00+00:00","computer_use":null,"uncensored":"2026-04-25T00:00:00+00:00","instruction_following":null,"writing":"2026-08-27T00:00:00+00:00","coding":"2026-07-13T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00","json":null,"math":"2026-07-13T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00"},"confidence":{"tool_use":0.0,"hallucination":0.47,"agentic":0.13,"long_context":0.0,"multimodal":0.22,"multilingual":0.0,"eq":0.0,"computer_use":0.0,"uncensored":0.2,"instruction_following":0.0,"writing":0.13,"coding":0.0,"reasoning":0.07,"json":0.0,"math":0.0,"overall":0.12},"sourceCounts":{"tool_use":0,"hallucination":1,"agentic":3,"long_context":0,"multimodal":1,"multilingual":1,"eq":2,"computer_use":0,"uncensored":4,"instruction_following":0,"writing":3,"coding":2,"reasoning":5,"json":0,"math":1,"overall":2},"inputCostPerMillion":5.0,"outputCostPerMillion":30.0,"contextWindowTokens":1050000,"medianLatencyMs":null,"outputTokensPerSecond":62.8774224691713,"bestFor":["Agentic","Factuality","Multimodal"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":4,"variantId":81,"modelSlug":"anthropic--claude-sonnet-4.6","modelName":"Anthropic: Claude Sonnet 4.6","providerSlug":"anthropic","providerName":"Anthropic","modelFamily":null,"openWeights":false,"overallScore":89.4,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"tool_use":59.3,"hallucination":null,"multilingual":93.7,"agentic":47.3,"eq":null,"uncensored":null,"computer_use":71.6,"long_context":null,"math":null,"multimodal":73.9,"instruction_following":null,"reasoning":67.0,"overall":89.4,"coding":56.1,"writing":null,"json":null},"freshness":{"tool_use":"2026-02-23T00:00:00+00:00","hallucination":null,"multilingual":"2026-07-28T12:18:16+00:00","agentic":"2026-07-06T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","uncensored":null,"computer_use":"2026-03-08T00:00:00+00:00","long_context":null,"math":"2026-07-13T00:00:00+00:00","multimodal":"2026-05-08T17:00:24.288943+00:00","instruction_following":null,"reasoning":"2026-07-13T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","json":null},"confidence":{"tool_use":0.44,"hallucination":0.0,"multilingual":0.38,"agentic":0.14,"eq":0.0,"uncensored":0.0,"computer_use":0.51,"long_context":0.0,"math":0.0,"multimodal":0.24,"instruction_following":0.0,"reasoning":0.08,"overall":0.12,"coding":0.05,"writing":0.0,"json":0.0},"sourceCounts":{"tool_use":2,"hallucination":0,"multilingual":2,"agentic":3,"eq":2,"uncensored":0,"computer_use":1,"long_context":0,"math":1,"multimodal":2,"instruction_following":0,"reasoning":6,"overall":2,"coding":6,"writing":2,"json":0},"inputCostPerMillion":3.0,"outputCostPerMillion":15.0,"contextWindowTokens":1000000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multilingual","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":5,"variantId":66,"modelSlug":"openai--gpt-5.4","modelName":"OpenAI: GPT-5.4","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":89.0,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"overall":89.0,"eq":null,"tool_use":null,"uncensored":57.6,"long_context":null,"writing":88.0,"instruction_following":null,"multimodal":79.7,"coding":null,"hallucination":92.0,"computer_use":null,"agentic":60.7,"json":null,"multilingual":null,"math":null,"reasoning":71.6},"freshness":{"overall":"2026-08-27T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","tool_use":null,"uncensored":"2026-03-05T00:00:00+00:00","long_context":null,"writing":"2026-08-27T00:00:00+00:00","instruction_following":null,"multimodal":"2000-01-01T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","hallucination":"2000-01-01T00:00:00+00:00","computer_use":null,"agentic":"2026-04-27T00:00:00+00:00","json":null,"multilingual":"2026-07-28T12:18:16+00:00","math":"2026-07-13T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00"},"confidence":{"overall":0.12,"eq":0.0,"tool_use":0.0,"uncensored":0.2,"long_context":0.0,"writing":0.13,"instruction_following":0.0,"multimodal":0.22,"coding":0.0,"hallucination":0.47,"computer_use":0.0,"agentic":0.13,"json":0.0,"multilingual":0.0,"math":0.0,"reasoning":0.07},"sourceCounts":{"overall":2,"eq":2,"tool_use":0,"uncensored":4,"long_context":0,"writing":3,"instruction_following":0,"multimodal":1,"coding":2,"hallucination":1,"computer_use":0,"agentic":2,"json":0,"multilingual":1,"math":1,"reasoning":5},"inputCostPerMillion":2.5,"outputCostPerMillion":15.0,"contextWindowTokens":1050000,"medianLatencyMs":null,"outputTokensPerSecond":84.7955330112953,"bestFor":["Factuality","Multimodal","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":6,"variantId":86,"modelSlug":"z-ai--glm-5","modelName":"Z.ai: GLM 5","providerSlug":"z-ai","providerName":"Z Ai","modelFamily":null,"openWeights":false,"overallScore":85.7,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"tool_use":null,"hallucination":null,"uncensored":null,"long_context":null,"multimodal":null,"instruction_following":null,"multilingual":null,"agentic":null,"computer_use":null,"eq":null,"math":null,"coding":65.2,"json":null,"writing":null,"overall":85.7,"reasoning":null},"freshness":{"tool_use":null,"hallucination":null,"uncensored":null,"long_context":null,"multimodal":null,"instruction_following":null,"multilingual":"2000-01-01T00:00:00+00:00","agentic":"2026-02-23T00:00:00+00:00","computer_use":null,"eq":null,"math":"2026-07-13T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","json":null,"writing":"2026-08-27T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00"},"confidence":{"tool_use":0.0,"hallucination":0.0,"uncensored":0.0,"long_context":0.0,"multimodal":0.0,"instruction_following":0.0,"multilingual":0.0,"agentic":0.0,"computer_use":0.0,"eq":0.0,"math":0.0,"coding":0.06,"json":0.0,"writing":0.0,"overall":0.12,"reasoning":0.0},"sourceCounts":{"tool_use":0,"hallucination":0,"uncensored":0,"long_context":0,"multimodal":0,"instruction_following":0,"multilingual":1,"agentic":1,"computer_use":0,"eq":0,"math":1,"coding":4,"json":0,"writing":2,"overall":2,"reasoning":2},"inputCostPerMillion":0.6,"outputCostPerMillion":1.92,"contextWindowTokens":204800,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":7,"variantId":130,"modelSlug":"anthropic--claude-opus-4.5","modelName":"Anthropic: Claude Opus 4.5","providerSlug":"anthropic","providerName":"Anthropic","modelFamily":null,"openWeights":false,"overallScore":85.5,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"computer_use":null,"json":46.1,"overall":85.5,"eq":null,"reasoning":71.6,"multilingual":93.1,"coding":68.8,"agentic":66.2,"instruction_following":null,"multimodal":75.0,"writing":84.0,"hallucination":null,"uncensored":null,"tool_use":43.0,"long_context":null,"math":null},"freshness":{"computer_use":null,"json":"2026-05-15T17:27:34.392962+00:00","overall":"2026-08-27T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00","multilingual":"2026-06-05T07:22:32+00:00","coding":"2026-08-21T00:00:00+00:00","agentic":"2026-01-29T00:00:00+00:00","instruction_following":null,"multimodal":"2026-05-15T17:28:02.763761+00:00","writing":"2026-08-27T00:00:00+00:00","hallucination":null,"uncensored":null,"tool_use":"2025-11-27T00:00:00+00:00","long_context":null,"math":"2026-07-13T00:00:00+00:00"},"confidence":{"computer_use":0.0,"json":0.21,"overall":0.12,"eq":0.0,"reasoning":0.06,"multilingual":0.38,"coding":0.06,"agentic":0.16,"instruction_following":0.0,"multimodal":0.26,"writing":0.14,"hallucination":0.0,"uncensored":0.0,"tool_use":0.34,"long_context":0.0,"math":0.0},"sourceCounts":{"computer_use":0,"json":4,"overall":2,"eq":2,"reasoning":6,"multilingual":2,"coding":4,"agentic":2,"instruction_following":0,"multimodal":1,"writing":3,"hallucination":0,"uncensored":0,"tool_use":1,"long_context":0,"math":1},"inputCostPerMillion":5.0,"outputCostPerMillion":25.0,"contextWindowTokens":200000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multilingual","Multimodal","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":8,"variantId":163,"modelSlug":"anthropic--claude-sonnet-4.5","modelName":"Anthropic: Claude Sonnet 4.5","providerSlug":"anthropic","providerName":"Anthropic","modelFamily":null,"openWeights":false,"overallScore":85.5,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"uncensored":null,"computer_use":62.4,"multilingual":92.1,"agentic":49.8,"reasoning":39.9,"coding":58.6,"hallucination":null,"json":28.6,"math":null,"writing":84.0,"instruction_following":null,"eq":null,"multimodal":76.3,"tool_use":38.4,"overall":85.5,"long_context":null},"freshness":{"uncensored":null,"computer_use":"2025-10-31T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","agentic":"2026-03-11T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","hallucination":null,"json":"2026-05-15T17:27:34.392962+00:00","math":"2026-07-13T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","instruction_following":null,"eq":"2000-01-01T00:00:00+00:00","multimodal":"2026-05-15T17:28:02.763728+00:00","tool_use":"2025-10-28T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","long_context":null},"confidence":{"uncensored":0.0,"computer_use":0.51,"multilingual":0.38,"agentic":0.13,"reasoning":0.05,"coding":0.06,"hallucination":0.0,"json":0.21,"math":0.0,"writing":0.14,"instruction_following":0.0,"eq":0.0,"multimodal":0.26,"tool_use":0.34,"overall":0.12,"long_context":0.0},"sourceCounts":{"uncensored":0,"computer_use":1,"multilingual":2,"agentic":3,"reasoning":6,"coding":4,"hallucination":0,"json":4,"math":1,"writing":3,"instruction_following":0,"eq":2,"multimodal":1,"tool_use":1,"overall":2,"long_context":0},"inputCostPerMillion":3.0,"outputCostPerMillion":15.0,"contextWindowTokens":1000000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multilingual","Multimodal","Overall"],"avoidFor":["Function Calling"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":9,"variantId":58,"modelSlug":"openai--gpt-5.4-mini","modelName":"OpenAI: GPT-5.4 Mini","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":83.2,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"tool_use":null,"hallucination":93.5,"multimodal":75.1,"coding":null,"overall":83.2,"json":null,"multilingual":null,"agentic":null,"math":null,"computer_use":null,"writing":null,"eq":null,"long_context":null,"reasoning":null,"uncensored":null,"instruction_following":null},"freshness":{"tool_use":null,"hallucination":"2000-01-01T00:00:00+00:00","multimodal":"2000-01-01T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","json":null,"multilingual":null,"agentic":null,"math":"2026-07-13T00:00:00+00:00","computer_use":null,"writing":"2026-08-27T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","long_context":null,"reasoning":"2026-07-13T00:00:00+00:00","uncensored":null,"instruction_following":null},"confidence":{"tool_use":0.0,"hallucination":0.47,"multimodal":0.22,"coding":0.0,"overall":0.12,"json":0.0,"multilingual":0.0,"agentic":0.0,"math":0.0,"computer_use":0.0,"writing":0.0,"eq":0.0,"long_context":0.0,"reasoning":0.0,"uncensored":0.0,"instruction_following":0.0},"sourceCounts":{"tool_use":0,"hallucination":1,"multimodal":1,"coding":2,"overall":2,"json":0,"multilingual":0,"agentic":0,"math":1,"computer_use":0,"writing":2,"eq":1,"long_context":0,"reasoning":4,"uncensored":0,"instruction_following":0},"inputCostPerMillion":0.75,"outputCostPerMillion":4.5,"contextWindowTokens":400000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality","Multimodal","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":10,"variantId":232,"modelSlug":"google--gemini-2.5-pro","modelName":"Google: Gemini 2.5 Pro","providerSlug":"google","providerName":"Google","modelFamily":null,"openWeights":false,"overallScore":82.0,"overallConfidence":0.12,"overallSourceCount":3,"scores":{"multilingual":92.0,"agentic":48.9,"eq":null,"reasoning":53.0,"coding":50.2,"hallucination":92.0,"uncensored":47.2,"computer_use":null,"json":null,"long_context":null,"math":null,"overall":82.0,"writing":75.2,"tool_use":10.0,"multimodal":78.1,"instruction_following":null},"freshness":{"multilingual":"2026-07-28T12:18:16+00:00","agentic":"2025-10-31T00:00:00+00:00","eq":null,"reasoning":"2026-07-13T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","hallucination":"2000-01-01T00:00:00+00:00","uncensored":"2025-09-09T00:00:00+00:00","computer_use":null,"json":null,"long_context":null,"math":"2026-07-13T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","tool_use":"2025-10-28T00:00:00+00:00","multimodal":"2000-01-01T00:00:00+00:00","instruction_following":null},"confidence":{"multilingual":0.38,"agentic":0.16,"eq":0.0,"reasoning":0.06,"coding":0.07,"hallucination":0.47,"uncensored":0.2,"computer_use":0.0,"json":0.0,"long_context":0.0,"math":0.0,"overall":0.12,"writing":0.14,"tool_use":0.34,"multimodal":0.24,"instruction_following":0.0},"sourceCounts":{"multilingual":2,"agentic":2,"eq":0,"reasoning":6,"coding":7,"hallucination":1,"uncensored":4,"computer_use":0,"json":0,"long_context":0,"math":2,"overall":3,"writing":4,"tool_use":1,"multimodal":1,"instruction_following":0},"inputCostPerMillion":1.25,"outputCostPerMillion":10.0,"contextWindowTokens":1048576,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality","Multilingual","Multimodal"],"avoidFor":["Tool Use"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":11,"variantId":278,"modelSlug":"google--gemini-2.0-flash-lite-001","modelName":"Google: Gemini 2.0 Flash Lite","providerSlug":"google","providerName":"Google","modelFamily":null,"openWeights":false,"overallScore":81.2,"overallConfidence":0.12,"overallSourceCount":1,"scores":{"multilingual":null,"agentic":null,"eq":null,"reasoning":68.6,"coding":46.8,"tool_use":null,"hallucination":null,"uncensored":null,"computer_use":null,"json":null,"long_context":null,"math":null,"overall":81.2,"multimodal":70.2,"instruction_following":null,"writing":null},"freshness":{"multilingual":null,"agentic":null,"eq":null,"reasoning":"2026-05-15T17:28:02.763848+00:00","coding":"2026-05-20T12:15:25.844976+00:00","tool_use":null,"hallucination":null,"uncensored":null,"computer_use":null,"json":null,"long_context":null,"math":"2025-05-01T00:00:00+00:00","overall":"2026-05-20T12:15:25.845017+00:00","multimodal":"2026-05-15T17:28:02.763848+00:00","instruction_following":null,"writing":"2026-05-20T12:15:25.845059+00:00"},"confidence":{"multilingual":0.0,"agentic":0.0,"eq":0.0,"reasoning":0.09,"coding":0.07,"tool_use":0.0,"hallucination":0.0,"uncensored":0.0,"computer_use":0.0,"json":0.0,"long_context":0.0,"math":0.0,"overall":0.12,"multimodal":0.26,"instruction_following":0.0,"writing":0.0},"sourceCounts":{"multilingual":0,"agentic":0,"eq":0,"reasoning":2,"coding":2,"tool_use":0,"hallucination":0,"uncensored":0,"computer_use":0,"json":0,"long_context":0,"math":1,"overall":1,"multimodal":1,"instruction_following":0,"writing":1},"inputCostPerMillion":0.075,"outputCostPerMillion":0.3,"contextWindowTokens":1048576,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-05-20T12:15:25.845017+00:00","hasRealData":true},{"rank":12,"variantId":135,"modelSlug":"openai--gpt-5.1","modelName":"OpenAI: GPT-5.1","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":81.1,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"uncensored":46.2,"long_context":null,"eq":null,"tool_use":null,"instruction_following":null,"multimodal":83.9,"agentic":60.8,"math":81.3,"reasoning":67.1,"json":null,"overall":81.1,"coding":60.4,"computer_use":null,"writing":80.1,"multilingual":null,"hallucination":null},"freshness":{"uncensored":"2025-11-16T00:00:00+00:00","long_context":null,"eq":"2000-01-01T00:00:00+00:00","tool_use":null,"instruction_following":null,"multimodal":"2026-05-15T17:28:02.763224+00:00","agentic":"2025-11-25T00:00:00+00:00","math":"2026-07-13T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00","json":null,"overall":"2026-08-27T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","computer_use":null,"writing":"2026-08-27T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","hallucination":null},"confidence":{"uncensored":0.2,"long_context":0.0,"eq":0.0,"tool_use":0.0,"instruction_following":0.0,"multimodal":0.26,"agentic":0.16,"math":0.12,"reasoning":0.08,"json":0.0,"overall":0.12,"coding":0.06,"computer_use":0.0,"writing":0.13,"multilingual":0.0,"hallucination":0.0},"sourceCounts":{"uncensored":4,"long_context":0,"eq":1,"tool_use":0,"instruction_following":0,"multimodal":1,"agentic":2,"math":3,"reasoning":7,"json":0,"overall":2,"coding":4,"computer_use":0,"writing":3,"multilingual":1,"hallucination":0},"inputCostPerMillion":1.25,"outputCostPerMillion":10.0,"contextWindowTokens":400000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Math","Multimodal","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":13,"variantId":113,"modelSlug":"openai--gpt-5.2","modelName":"OpenAI: GPT-5.2","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":81.0,"overallConfidence":0.12,"overallSourceCount":2,"scores":{"instruction_following":null,"multilingual":92.2,"agentic":null,"eq":null,"reasoning":66.5,"coding":69.9,"tool_use":null,"hallucination":null,"uncensored":39.3,"computer_use":null,"json":54.2,"long_context":null,"math":null,"overall":81.0,"writing":79.8,"multimodal":78.0},"freshness":{"instruction_following":null,"multilingual":"2026-07-28T12:18:16+00:00","agentic":"2025-12-24T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","tool_use":null,"hallucination":null,"uncensored":"2026-03-04T00:00:00+00:00","computer_use":null,"json":"2026-05-15T17:27:34.392962+00:00","long_context":null,"math":"2026-07-13T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","multimodal":"2000-01-01T00:00:00+00:00"},"confidence":{"instruction_following":0.0,"multilingual":0.38,"agentic":0.0,"eq":0.0,"reasoning":0.06,"coding":0.06,"tool_use":0.0,"hallucination":0.0,"uncensored":0.2,"computer_use":0.0,"json":0.21,"long_context":0.0,"math":0.0,"overall":0.12,"writing":0.12,"multimodal":0.22},"sourceCounts":{"instruction_following":0,"multilingual":2,"agentic":1,"eq":2,"reasoning":7,"coding":4,"tool_use":0,"hallucination":0,"uncensored":4,"computer_use":0,"json":4,"long_context":0,"math":2,"overall":2,"writing":4,"multimodal":1},"inputCostPerMillion":1.75,"outputCostPerMillion":14.0,"contextWindowTokens":400000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multilingual","Multimodal","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":14,"variantId":27,"modelSlug":"deepseek--deepseek-v4-flash","modelName":"DeepSeek: DeepSeek V4 Flash 0423","providerSlug":"deepseek","providerName":"Deepseek","modelFamily":null,"openWeights":false,"overallScore":80.9,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"tool_use":50.4,"hallucination":null,"uncensored":null,"computer_use":null,"long_context":null,"multimodal":null,"instruction_following":null,"eq":null,"multilingual":null,"agentic":null,"writing":null,"coding":null,"reasoning":null,"json":null,"math":null,"overall":80.9},"freshness":{"tool_use":"2026-07-30T00:00:00+00:00","hallucination":null,"uncensored":null,"computer_use":null,"long_context":null,"multimodal":null,"instruction_following":null,"eq":"2000-01-01T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","agentic":"2026-08-15T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","coding":"2026-07-13T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00","json":null,"math":"2026-07-13T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00"},"confidence":{"tool_use":0.34,"hallucination":0.0,"uncensored":0.0,"computer_use":0.0,"long_context":0.0,"multimodal":0.0,"instruction_following":0.0,"eq":0.0,"multilingual":0.0,"agentic":0.0,"writing":0.0,"coding":0.0,"reasoning":0.0,"json":0.0,"math":0.0,"overall":0.21},"sourceCounts":{"tool_use":1,"hallucination":0,"uncensored":0,"computer_use":0,"long_context":0,"multimodal":0,"instruction_following":0,"eq":2,"multilingual":1,"agentic":1,"writing":1,"coding":3,"reasoning":3,"json":0,"math":1,"overall":1},"inputCostPerMillion":0.0854,"outputCostPerMillion":0.1708,"contextWindowTokens":1048576,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":15,"variantId":26,"modelSlug":"deepseek--deepseek-v4-pro","modelName":"DeepSeek: DeepSeek V4 Pro 0423","providerSlug":"deepseek","providerName":"Deepseek","modelFamily":null,"openWeights":false,"overallScore":80.4,"overallConfidence":0.17,"overallSourceCount":2,"scores":{"multilingual":null,"eq":null,"tool_use":55.4,"hallucination":90.4,"uncensored":null,"computer_use":null,"long_context":null,"multimodal":null,"instruction_following":null,"agentic":null,"writing":72.2,"coding":74.7,"reasoning":null,"json":null,"math":null,"overall":80.4},"freshness":{"multilingual":null,"eq":"2000-01-01T00:00:00+00:00","tool_use":"2026-06-30T00:00:00+00:00","hallucination":"2000-01-01T00:00:00+00:00","uncensored":null,"computer_use":null,"long_context":null,"multimodal":null,"instruction_following":null,"agentic":"2026-06-08T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","reasoning":"2026-07-13T00:00:00+00:00","json":null,"math":"2026-07-13T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00"},"confidence":{"multilingual":0.0,"eq":0.0,"tool_use":0.34,"hallucination":0.47,"uncensored":0.0,"computer_use":0.0,"long_context":0.0,"multimodal":0.0,"instruction_following":0.0,"agentic":0.0,"writing":0.23,"coding":0.07,"reasoning":0.0,"json":0.0,"math":0.0,"overall":0.17},"sourceCounts":{"multilingual":0,"eq":2,"tool_use":1,"hallucination":1,"uncensored":0,"computer_use":0,"long_context":0,"multimodal":0,"instruction_following":0,"agentic":1,"writing":2,"coding":5,"reasoning":3,"json":0,"math":1,"overall":2},"inputCostPerMillion":0.7010460000000001,"outputCostPerMillion":1.4020920000000001,"contextWindowTokens":1048576,"medianLatencyMs":null,"outputTokensPerSecond":29.1463293721532,"bestFor":["Factuality","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":16,"variantId":128,"modelSlug":"deepseek--deepseek-v3.2","modelName":"DeepSeek: DeepSeek V3.2","providerSlug":"deepseek","providerName":"Deepseek","modelFamily":null,"openWeights":false,"overallScore":80.3,"overallConfidence":0.17,"overallSourceCount":2,"scores":{"multimodal":null,"instruction_following":null,"overall":80.3,"multilingual":null,"uncensored":null,"computer_use":null,"long_context":null,"tool_use":null,"agentic":34.7,"reasoning":54.5,"coding":49.5,"json":47.0,"writing":70.7,"math":87.7,"hallucination":92.7,"eq":null},"freshness":{"multimodal":null,"instruction_following":null,"overall":"2026-08-27T00:00:00+00:00","multilingual":"2000-01-01T00:00:00+00:00","uncensored":null,"computer_use":null,"long_context":null,"tool_use":null,"agentic":"2026-02-10T00:00:00+00:00","reasoning":"2025-05-01T00:00:00+00:00","coding":"2026-08-21T00:00:00+00:00","json":"2026-05-15T17:27:34.392962+00:00","writing":"2026-08-27T00:00:00+00:00","math":"2025-05-01T00:00:00+00:00","hallucination":"2000-01-01T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00"},"confidence":{"multimodal":0.0,"instruction_following":0.0,"overall":0.17,"multilingual":0.0,"uncensored":0.0,"computer_use":0.0,"long_context":0.0,"tool_use":0.0,"agentic":0.16,"reasoning":0.11,"coding":0.08,"json":0.21,"writing":0.23,"math":0.16,"hallucination":0.47,"eq":0.0},"sourceCounts":{"multimodal":0,"instruction_following":0,"overall":2,"multilingual":1,"uncensored":0,"computer_use":0,"long_context":0,"tool_use":0,"agentic":2,"reasoning":2,"coding":5,"json":4,"writing":2,"math":2,"hallucination":1,"eq":1},"inputCostPerMillion":0.26,"outputCostPerMillion":0.38,"contextWindowTokens":163840,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality","Math","Overall"],"avoidFor":["Agentic"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":17,"variantId":254,"modelSlug":"openai--o3","modelName":"OpenAI: o3","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":79.8,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"multilingual":null,"agentic":null,"eq":null,"tool_use":null,"hallucination":null,"uncensored":49.6,"computer_use":22.5,"long_context":null,"instruction_following":null,"multimodal":81.3,"coding":null,"writing":79.4,"math":null,"reasoning":78.4,"json":42.4,"overall":79.8},"freshness":{"multilingual":"2026-08-26T14:16:42.406538+00:00","agentic":"2025-10-19T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","tool_use":null,"hallucination":null,"uncensored":"2025-09-24T00:00:00+00:00","computer_use":"2025-07-28T00:00:00+00:00","long_context":null,"instruction_following":null,"multimodal":"2000-01-01T00:00:00+00:00","coding":"2026-02-15T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","math":"2025-05-01T00:00:00+00:00","reasoning":"2025-09-24T00:00:00+00:00","json":"2026-05-15T17:27:34.392962+00:00","overall":"2026-08-27T00:00:00+00:00"},"confidence":{"multilingual":0.0,"agentic":0.0,"eq":0.0,"tool_use":0.0,"hallucination":0.0,"uncensored":0.2,"computer_use":0.51,"long_context":0.0,"instruction_following":0.0,"multimodal":0.22,"coding":0.0,"writing":0.18,"math":0.0,"reasoning":0.06,"json":0.21,"overall":0.21},"sourceCounts":{"multilingual":1,"agentic":1,"eq":2,"tool_use":0,"hallucination":0,"uncensored":4,"computer_use":1,"long_context":0,"instruction_following":0,"multimodal":3,"coding":1,"writing":2,"math":1,"reasoning":3,"json":4,"overall":1},"inputCostPerMillion":2.0,"outputCostPerMillion":8.0,"contextWindowTokens":200000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multimodal","Overall","Reasoning"],"avoidFor":["Computer Use"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":18,"variantId":256,"modelSlug":"openai--gpt-4.1","modelName":"OpenAI: GPT-4.1","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":78.1,"overallConfidence":0.12,"overallSourceCount":3,"scores":{"multilingual":null,"agentic":null,"eq":null,"uncensored":46.6,"json":47.3,"long_context":null,"math":null,"overall":78.1,"writing":75.7,"multimodal":72.6,"reasoning":63.5,"coding":null,"tool_use":null,"hallucination":92.6,"computer_use":null,"instruction_following":87.4},"freshness":{"multilingual":"2026-08-26T14:16:42.406538+00:00","agentic":"2025-08-11T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","uncensored":"2025-09-24T00:00:00+00:00","json":"2026-05-15T17:27:34.392962+00:00","long_context":null,"math":"2025-05-01T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","multimodal":"2000-01-01T00:00:00+00:00","reasoning":"2026-07-09T00:00:00+00:00","coding":"2026-07-09T00:00:00+00:00","tool_use":null,"hallucination":"2000-01-01T00:00:00+00:00","computer_use":null,"instruction_following":"2000-01-01T00:00:00+00:00"},"confidence":{"multilingual":0.0,"agentic":0.0,"eq":0.0,"uncensored":0.2,"json":0.21,"long_context":0.0,"math":0.0,"overall":0.12,"writing":0.13,"multimodal":0.22,"reasoning":0.06,"coding":0.0,"tool_use":0.0,"hallucination":0.28,"computer_use":0.0,"instruction_following":0.8},"sourceCounts":{"multilingual":2,"agentic":1,"eq":2,"uncensored":4,"json":4,"long_context":0,"math":1,"overall":3,"writing":3,"multimodal":2,"reasoning":8,"coding":2,"tool_use":0,"hallucination":2,"computer_use":0,"instruction_following":1},"inputCostPerMillion":2.0,"outputCostPerMillion":8.0,"contextWindowTokens":1047576,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality","Instruction Following","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":19,"variantId":262,"modelSlug":"meta-llama--llama-4-maverick","modelName":"Meta: Llama 4 Maverick","providerSlug":"meta-llama","providerName":"Meta Llama","modelFamily":null,"openWeights":false,"overallScore":76.6,"overallConfidence":0.12,"overallSourceCount":1,"scores":{"json":48.0,"hallucination":null,"computer_use":null,"agentic":null,"multilingual":86.4,"uncensored":null,"math":null,"multimodal":68.8,"reasoning":50.2,"writing":47.4,"coding":42.1,"overall":76.6,"tool_use":null,"eq":null,"long_context":null,"instruction_following":null},"freshness":{"json":"2026-05-15T17:27:34.392962+00:00","hallucination":null,"computer_use":null,"agentic":null,"multilingual":"2026-07-28T12:18:16+00:00","uncensored":null,"math":"2000-01-01T00:00:00+00:00","multimodal":"2026-05-15T17:28:02.765194+00:00","reasoning":"2026-05-15T17:28:02.765194+00:00","writing":"2026-05-20T12:15:25.849687+00:00","coding":"2026-05-20T12:15:25.849603+00:00","overall":"2026-05-20T12:15:25.849646+00:00","tool_use":null,"eq":null,"long_context":null,"instruction_following":null},"confidence":{"json":0.21,"hallucination":0.0,"computer_use":0.0,"agentic":0.0,"multilingual":0.29,"uncensored":0.0,"math":0.0,"multimodal":0.22,"reasoning":0.04,"writing":0.11,"coding":0.08,"overall":0.12,"tool_use":0.0,"eq":0.0,"long_context":0.0,"instruction_following":0.0},"sourceCounts":{"json":4,"hallucination":0,"computer_use":0,"agentic":0,"multilingual":3,"uncensored":0,"math":1,"multimodal":3,"reasoning":3,"writing":2,"coding":5,"overall":1,"tool_use":0,"eq":0,"long_context":0,"instruction_following":0},"inputCostPerMillion":0.19999999999999998,"outputCostPerMillion":0.7999999999999999,"contextWindowTokens":1048576,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multilingual","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-05-20T12:15:25.849646+00:00","hasRealData":true},{"rank":20,"variantId":139,"modelSlug":"moonshotai--kimi-k2-thinking","modelName":"MoonshotAI: Kimi K2 Thinking","providerSlug":"moonshotai","providerName":"Moonshotai","modelFamily":null,"openWeights":false,"overallScore":76.4,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"computer_use":null,"eq":null,"multilingual":null,"hallucination":null,"long_context":null,"multimodal":null,"instruction_following":null,"uncensored":45.3,"overall":76.4,"math":null,"writing":74.8,"reasoning":65.5,"coding":51.3,"json":64.3,"tool_use":null,"agentic":null},"freshness":{"computer_use":null,"eq":"2000-01-01T00:00:00+00:00","multilingual":"2000-01-01T00:00:00+00:00","hallucination":null,"long_context":null,"multimodal":null,"instruction_following":null,"uncensored":"2025-11-07T00:00:00+00:00","overall":"2026-05-19T00:00:00+00:00","math":"2000-01-01T00:00:00+00:00","writing":"2026-05-19T00:00:00+00:00","reasoning":"2025-11-07T00:00:00+00:00","coding":"2025-11-11T00:00:00+00:00","json":"2026-05-15T17:27:34.392962+00:00","tool_use":null,"agentic":"2025-11-11T00:00:00+00:00"},"confidence":{"computer_use":0.0,"eq":0.0,"multilingual":0.0,"hallucination":0.0,"long_context":0.0,"multimodal":0.0,"instruction_following":0.0,"uncensored":0.2,"overall":0.21,"math":0.0,"writing":0.18,"reasoning":0.1,"coding":0.11,"json":0.21,"tool_use":0.0,"agentic":0.0},"sourceCounts":{"computer_use":0,"eq":1,"multilingual":1,"hallucination":0,"long_context":0,"multimodal":0,"instruction_following":0,"uncensored":4,"overall":1,"math":1,"writing":2,"reasoning":3,"coding":3,"json":4,"tool_use":0,"agentic":1},"inputCostPerMillion":0.6,"outputCostPerMillion":2.5,"contextWindowTokens":262144,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-05-19T00:00:00+00:00","hasRealData":true},{"rank":21,"variantId":197,"modelSlug":"openai--gpt-5","modelName":"OpenAI: GPT-5","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":75.6,"overallConfidence":0.12,"overallSourceCount":3,"scores":{"multilingual":null,"agentic":54.4,"eq":null,"tool_use":null,"hallucination":null,"uncensored":45.6,"computer_use":0.3,"long_context":null,"multimodal":64.5,"instruction_following":null,"coding":48.0,"overall":75.6,"reasoning":39.6,"json":null,"math":85.5,"writing":69.3},"freshness":{"multilingual":"2026-07-28T12:18:16+00:00","agentic":"2025-12-03T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","tool_use":null,"hallucination":null,"uncensored":"2025-09-24T00:00:00+00:00","computer_use":"2026-04-14T00:00:00+00:00","long_context":null,"multimodal":"2026-05-15T17:28:02.764070+00:00","instruction_following":null,"coding":"2026-05-20T12:15:25.847711+00:00","overall":"2026-05-20T12:15:25.847752+00:00","reasoning":"2026-05-15T17:28:02.764070+00:00","json":null,"math":"2025-05-01T00:00:00+00:00","writing":"2026-05-20T12:15:25.847794+00:00"},"confidence":{"multilingual":0.0,"agentic":0.13,"eq":0.0,"tool_use":0.0,"hallucination":0.0,"uncensored":0.2,"computer_use":0.34,"long_context":0.0,"multimodal":0.24,"instruction_following":0.0,"coding":0.09,"overall":0.12,"reasoning":0.08,"json":0.0,"math":0.16,"writing":0.15},"sourceCounts":{"multilingual":1,"agentic":3,"eq":1,"tool_use":0,"hallucination":0,"uncensored":4,"computer_use":1,"long_context":0,"multimodal":2,"instruction_following":0,"coding":5,"overall":3,"reasoning":7,"json":0,"math":3,"writing":4},"inputCostPerMillion":1.25,"outputCostPerMillion":10.0,"contextWindowTokens":400000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Math","Overall"],"avoidFor":["Computer Use"],"scoredAt":null,"lastUpdated":"2026-05-20T12:15:25.847752+00:00","hasRealData":true},{"rank":22,"variantId":150,"modelSlug":"anthropic--claude-haiku-4.5","modelName":"Anthropic: Claude Haiku 4.5","providerSlug":"anthropic","providerName":"Anthropic","modelFamily":null,"openWeights":false,"overallScore":75.3,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"computer_use":16.5,"agentic":null,"uncensored":null,"long_context":null,"eq":null,"math":null,"reasoning":null,"writing":null,"multimodal":null,"tool_use":25.7,"instruction_following":null,"json":29.4,"overall":75.3,"multilingual":88.7,"coding":53.6,"hallucination":null},"freshness":{"computer_use":"2026-04-14T00:00:00+00:00","agentic":"2025-12-11T00:00:00+00:00","uncensored":null,"long_context":null,"eq":null,"math":null,"reasoning":null,"writing":"2026-08-27T00:00:00+00:00","multimodal":null,"tool_use":"2025-10-28T00:00:00+00:00","instruction_following":null,"json":"2026-05-15T17:27:34.392962+00:00","overall":"2026-08-27T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","coding":"2026-08-21T00:00:00+00:00","hallucination":null},"confidence":{"computer_use":0.34,"agentic":0.0,"uncensored":0.0,"long_context":0.0,"eq":0.0,"math":0.0,"reasoning":0.0,"writing":0.0,"multimodal":0.0,"tool_use":0.34,"instruction_following":0.0,"json":0.21,"overall":0.21,"multilingual":0.38,"coding":0.08,"hallucination":0.0},"sourceCounts":{"computer_use":1,"agentic":1,"uncensored":0,"long_context":0,"eq":0,"math":0,"reasoning":0,"writing":1,"multimodal":0,"tool_use":1,"instruction_following":0,"json":4,"overall":1,"multilingual":2,"coding":3,"hallucination":0},"inputCostPerMillion":1.0,"outputCostPerMillion":5.0,"contextWindowTokens":200000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multilingual","Overall"],"avoidFor":["Computer Use","Function Calling"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":23,"variantId":305,"modelSlug":"openai--o1","modelName":"OpenAI: o1","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":75.1,"overallConfidence":0.17,"overallSourceCount":2,"scores":{"uncensored":45.1,"eq":null,"math":88.9,"reasoning":71.7,"writing":73.5,"tool_use":null,"instruction_following":null,"json":null,"overall":75.1,"multilingual":null,"multimodal":74.0,"coding":56.0,"hallucination":null,"computer_use":null,"long_context":null,"agentic":null},"freshness":{"uncensored":"2025-09-24T00:00:00+00:00","eq":null,"math":"2025-05-01T00:00:00+00:00","reasoning":"2025-09-24T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","tool_use":null,"instruction_following":null,"json":null,"overall":"2026-08-27T00:00:00+00:00","multilingual":"2026-08-26T14:16:42.406538+00:00","multimodal":"2000-01-01T00:00:00+00:00","coding":"2026-05-20T12:15:25.851897+00:00","hallucination":"2000-01-01T00:00:00+00:00","computer_use":null,"long_context":null,"agentic":"2025-02-10T00:00:00+00:00"},"confidence":{"uncensored":0.2,"eq":0.0,"math":0.13,"reasoning":0.08,"writing":0.17,"tool_use":0.0,"instruction_following":0.0,"json":0.0,"overall":0.17,"multilingual":0.0,"multimodal":0.22,"coding":0.08,"hallucination":0.0,"computer_use":0.0,"long_context":0.0,"agentic":0.0},"sourceCounts":{"uncensored":4,"eq":0,"math":2,"reasoning":5,"writing":3,"tool_use":0,"instruction_following":0,"json":0,"overall":2,"multilingual":1,"multimodal":2,"coding":5,"hallucination":1,"computer_use":0,"long_context":0,"agentic":1},"inputCostPerMillion":15.0,"outputCostPerMillion":60.0,"contextWindowTokens":200000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Math","Overall"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":24,"variantId":231,"modelSlug":"google--gemini-2.5-flash","modelName":"Google: Gemini 2.5 Flash","providerSlug":"google","providerName":"Google","modelFamily":null,"openWeights":false,"overallScore":74.4,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"coding":null,"agentic":21.3,"eq":null,"hallucination":91.2,"uncensored":null,"computer_use":null,"json":53.4,"long_context":null,"math":null,"overall":74.4,"writing":null,"multimodal":78.2,"instruction_following":null,"reasoning":29.3,"multilingual":58.7,"tool_use":3.2},"freshness":{"coding":"2025-11-03T00:00:00+00:00","agentic":"2025-11-03T00:00:00+00:00","eq":null,"hallucination":"2000-01-01T00:00:00+00:00","uncensored":null,"computer_use":null,"json":"2026-05-15T17:27:34.392962+00:00","long_context":null,"math":null,"overall":"2026-08-27T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","multimodal":"2000-01-01T00:00:00+00:00","instruction_following":null,"reasoning":"2025-04-03T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","tool_use":"2025-10-28T00:00:00+00:00"},"confidence":{"coding":0.0,"agentic":0.16,"eq":0.0,"hallucination":0.47,"uncensored":0.0,"computer_use":0.0,"json":0.21,"long_context":0.0,"math":0.0,"overall":0.21,"writing":0.0,"multimodal":0.24,"instruction_following":0.0,"reasoning":0.11,"multilingual":0.38,"tool_use":0.34},"sourceCounts":{"coding":1,"agentic":2,"eq":0,"hallucination":1,"uncensored":0,"computer_use":0,"json":4,"long_context":0,"math":0,"overall":1,"writing":1,"multimodal":1,"instruction_following":0,"reasoning":2,"multilingual":2,"tool_use":1},"inputCostPerMillion":0.3,"outputCostPerMillion":2.5,"contextWindowTokens":1048576,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality","Multimodal"],"avoidFor":["Agentic","Reasoning"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":25,"variantId":299,"modelSlug":"deepseek--deepseek-r1","modelName":"DeepSeek: R1","providerSlug":"deepseek","providerName":"Deepseek","modelFamily":null,"openWeights":false,"overallScore":73.7,"overallConfidence":0.17,"overallSourceCount":2,"scores":{"coding":55.0,"computer_use":null,"long_context":null,"eq":null,"reasoning":36.4,"tool_use":null,"json":null,"writing":65.3,"hallucination":87.7,"multimodal":null,"uncensored":45.6,"instruction_following":null,"math":null,"overall":73.7,"multilingual":null,"agentic":null},"freshness":{"coding":"2026-05-20T12:15:25.840534+00:00","computer_use":null,"long_context":null,"eq":"2000-01-01T00:00:00+00:00","reasoning":"2025-09-21T00:00:00+00:00","tool_use":null,"json":null,"writing":"2026-08-27T00:00:00+00:00","hallucination":"2000-01-01T00:00:00+00:00","multimodal":null,"uncensored":"2025-09-21T00:00:00+00:00","instruction_following":null,"math":"2025-05-01T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","multilingual":null,"agentic":null},"confidence":{"coding":0.08,"computer_use":0.0,"long_context":0.0,"eq":0.0,"reasoning":0.09,"tool_use":0.0,"json":0.0,"writing":0.17,"hallucination":0.47,"multimodal":0.0,"uncensored":0.2,"instruction_following":0.0,"math":0.0,"overall":0.17,"multilingual":0.0,"agentic":0.0},"sourceCounts":{"coding":4,"computer_use":0,"long_context":0,"eq":2,"reasoning":3,"tool_use":0,"json":0,"writing":3,"hallucination":1,"multimodal":0,"uncensored":4,"instruction_following":0,"math":1,"overall":2,"multilingual":0,"agentic":0},"inputCostPerMillion":0.7,"outputCostPerMillion":2.5,"contextWindowTokens":64000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":26,"variantId":255,"modelSlug":"openai--o4-mini","modelName":"OpenAI: o4 Mini","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":69.6,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"agentic":null,"eq":null,"tool_use":null,"hallucination":null,"uncensored":36.9,"long_context":null,"overall":69.6,"multimodal":81.8,"instruction_following":null,"coding":59.3,"computer_use":null,"multilingual":null,"math":null,"writing":68.3,"json":50.6,"reasoning":72.4},"freshness":{"agentic":"2025-05-24T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","tool_use":null,"hallucination":null,"uncensored":"2025-10-04T00:00:00+00:00","long_context":null,"overall":"2026-08-27T00:00:00+00:00","multimodal":"2000-01-01T00:00:00+00:00","instruction_following":null,"coding":"2026-02-15T00:00:00+00:00","computer_use":null,"multilingual":"2026-08-26T14:16:42.406538+00:00","math":"2000-01-01T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","json":"2026-05-15T17:27:34.392962+00:00","reasoning":"2025-10-04T00:00:00+00:00"},"confidence":{"agentic":0.0,"eq":0.0,"tool_use":0.0,"hallucination":0.0,"uncensored":0.2,"long_context":0.0,"overall":0.21,"multimodal":0.22,"instruction_following":0.0,"coding":0.13,"computer_use":0.0,"multilingual":0.0,"math":0.0,"writing":0.18,"json":0.21,"reasoning":0.04},"sourceCounts":{"agentic":1,"eq":1,"tool_use":0,"hallucination":0,"uncensored":4,"long_context":0,"overall":1,"multimodal":2,"instruction_following":0,"coding":2,"computer_use":0,"multilingual":1,"math":1,"writing":2,"json":4,"reasoning":2},"inputCostPerMillion":1.1,"outputCostPerMillion":4.4,"contextWindowTokens":200000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Multimodal"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":27,"variantId":239,"modelSlug":"anthropic--claude-sonnet-4","modelName":"Anthropic: Claude Sonnet 4","providerSlug":"anthropic","providerName":"Anthropic","modelFamily":null,"openWeights":false,"overallScore":69.6,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"uncensored":32.0,"tool_use":null,"multilingual":null,"hallucination":88.7,"computer_use":null,"reasoning":67.1,"coding":null,"overall":69.6,"writing":69.8,"json":null,"math":null,"instruction_following":null,"eq":null,"agentic":null,"multimodal":72.9,"long_context":null},"freshness":{"uncensored":"2025-09-12T00:00:00+00:00","tool_use":null,"multilingual":"2026-07-28T12:18:16+00:00","hallucination":"2000-01-01T00:00:00+00:00","computer_use":null,"reasoning":"2026-05-15T17:28:02.763746+00:00","coding":null,"overall":"2026-08-27T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","json":null,"math":null,"instruction_following":null,"eq":null,"agentic":"2025-06-09T00:00:00+00:00","multimodal":"2026-05-15T17:28:02.763746+00:00","long_context":null},"confidence":{"uncensored":0.2,"tool_use":0.0,"multilingual":0.0,"hallucination":0.47,"computer_use":0.0,"reasoning":0.04,"coding":0.0,"overall":0.21,"writing":0.18,"json":0.0,"math":0.0,"instruction_following":0.0,"eq":0.0,"agentic":0.0,"multimodal":0.26,"long_context":0.0},"sourceCounts":{"uncensored":4,"tool_use":0,"multilingual":1,"hallucination":1,"computer_use":0,"reasoning":2,"coding":0,"overall":1,"writing":2,"json":0,"math":0,"instruction_following":0,"eq":0,"agentic":1,"multimodal":1,"long_context":0},"inputCostPerMillion":3.0,"outputCostPerMillion":15.0,"contextWindowTokens":1000000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality"],"avoidFor":["Uncensored"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":28,"variantId":294,"modelSlug":"openai--o3-mini","modelName":"OpenAI: o3 Mini","providerSlug":"openai","providerName":"Openai","modelFamily":null,"openWeights":false,"overallScore":69.5,"overallConfidence":0.15,"overallSourceCount":3,"scores":{"eq":null,"multimodal":null,"computer_use":null,"tool_use":null,"json":null,"agentic":null,"uncensored":null,"long_context":null,"multilingual":null,"hallucination":null,"math":89.6,"reasoning":72.5,"instruction_following":93.9,"coding":63.5,"overall":69.5,"writing":55.4},"freshness":{"eq":null,"multimodal":null,"computer_use":null,"tool_use":null,"json":null,"agentic":null,"uncensored":null,"long_context":null,"multilingual":"2026-08-26T14:16:42.406538+00:00","hallucination":"2000-01-01T00:00:00+00:00","math":"2025-05-01T00:00:00+00:00","reasoning":"2025-07-01T00:00:00+00:00","instruction_following":"2000-01-01T00:00:00+00:00","coding":"2026-05-20T12:15:25.852273+00:00","overall":"2026-08-27T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00"},"confidence":{"eq":0.0,"multimodal":0.0,"computer_use":0.0,"tool_use":0.0,"json":0.0,"agentic":0.0,"uncensored":0.0,"long_context":0.0,"multilingual":0.0,"hallucination":0.0,"math":0.13,"reasoning":0.1,"instruction_following":0.8,"coding":0.08,"overall":0.15,"writing":0.23},"sourceCounts":{"eq":0,"multimodal":0,"computer_use":0,"tool_use":0,"json":0,"agentic":0,"uncensored":0,"long_context":0,"multilingual":1,"hallucination":1,"math":2,"reasoning":3,"instruction_following":1,"coding":2,"overall":3,"writing":2},"inputCostPerMillion":1.1,"outputCostPerMillion":4.4,"contextWindowTokens":200000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Instruction Following","Math"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":29,"variantId":311,"modelSlug":"amazon--nova-pro-v1","modelName":"Amazon: Nova Pro 1.0","providerSlug":"amazon","providerName":"Amazon","modelFamily":null,"openWeights":false,"overallScore":67.1,"overallConfidence":0.12,"overallSourceCount":1,"scores":{"agentic":null,"uncensored":null,"long_context":null,"eq":null,"math":null,"reasoning":null,"instruction_following":null,"json":39.2,"coding":36.9,"hallucination":null,"computer_use":null,"writing":null,"multilingual":null,"multimodal":60.5,"overall":67.1,"tool_use":null},"freshness":{"agentic":null,"uncensored":null,"long_context":null,"eq":null,"math":null,"reasoning":"2026-05-15T17:28:02.766143+00:00","instruction_following":null,"json":"2026-05-15T17:27:34.392962+00:00","coding":"2026-05-20T12:15:25.837424+00:00","hallucination":null,"computer_use":null,"writing":"2026-05-20T12:15:25.837513+00:00","multilingual":"2026-07-28T12:18:16+00:00","multimodal":"2026-05-15T17:28:02.766143+00:00","overall":"2026-05-20T12:15:25.837468+00:00","tool_use":null},"confidence":{"agentic":0.0,"uncensored":0.0,"long_context":0.0,"eq":0.0,"math":0.0,"reasoning":0.0,"instruction_following":0.0,"json":0.21,"coding":0.07,"hallucination":0.0,"computer_use":0.0,"writing":0.0,"multilingual":0.0,"multimodal":0.26,"overall":0.12,"tool_use":0.0},"sourceCounts":{"agentic":0,"uncensored":0,"long_context":0,"eq":0,"math":0,"reasoning":1,"instruction_following":0,"json":4,"coding":2,"hallucination":0,"computer_use":0,"writing":1,"multilingual":1,"multimodal":1,"overall":1,"tool_use":0},"inputCostPerMillion":0.7999999999999999,"outputCostPerMillion":3.1999999999999997,"contextWindowTokens":300000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":[],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-05-20T12:15:25.837468+00:00","hasRealData":true},{"rank":30,"variantId":353,"modelSlug":"mistralai--mistral-large","modelName":"Mistral Large","providerSlug":"mistralai","providerName":"Mistralai","modelFamily":null,"openWeights":false,"overallScore":66.6,"overallConfidence":0.09,"overallSourceCount":3,"scores":{"instruction_following":null,"json":42.2,"hallucination":null,"computer_use":null,"uncensored":56.1,"long_context":null,"eq":null,"math":null,"reasoning":59.8,"writing":39.9,"tool_use":null,"overall":66.6,"multilingual":null,"multimodal":null,"coding":26.9,"agentic":null},"freshness":{"instruction_following":"2026-05-08T17:00:35.652802+00:00","json":"2026-05-15T17:27:34.392962+00:00","hallucination":null,"computer_use":null,"uncensored":"2025-09-30T00:00:00+00:00","long_context":null,"eq":null,"math":"2026-05-08T17:00:35.652809+00:00","reasoning":"2026-05-08T17:00:35.652805+00:00","writing":"2026-05-20T12:15:25.850724+00:00","tool_use":null,"overall":"2026-05-20T12:15:25.850682+00:00","multilingual":null,"multimodal":null,"coding":"2026-05-20T12:15:25.850641+00:00","agentic":null},"confidence":{"instruction_following":0.0,"json":0.21,"hallucination":0.0,"computer_use":0.0,"uncensored":0.2,"long_context":0.0,"eq":0.0,"math":0.0,"reasoning":0.05,"writing":0.11,"tool_use":0.0,"overall":0.09,"multilingual":0.0,"multimodal":0.0,"coding":0.08,"agentic":0.0},"sourceCounts":{"instruction_following":1,"json":4,"hallucination":0,"computer_use":0,"uncensored":4,"long_context":0,"eq":0,"math":2,"reasoning":3,"writing":2,"tool_use":0,"overall":3,"multilingual":0,"multimodal":0,"coding":2,"agentic":0},"inputCostPerMillion":2.0,"outputCostPerMillion":6.0,"contextWindowTokens":128000,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":[],"avoidFor":["Coding"],"scoredAt":null,"lastUpdated":"2026-05-20T12:15:25.850682+00:00","hasRealData":true},{"rank":31,"variantId":252,"modelSlug":"qwen--qwen3-235b-a22b","modelName":"Qwen: Qwen3 235B A22B","providerSlug":"qwen","providerName":"Qwen","modelFamily":null,"openWeights":false,"overallScore":65.7,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"uncensored":36.7,"math":null,"tool_use":null,"multilingual":null,"hallucination":89.7,"computer_use":null,"long_context":null,"coding":null,"reasoning":null,"writing":65.0,"overall":65.7,"eq":null,"json":null,"multimodal":null,"agentic":null,"instruction_following":null},"freshness":{"uncensored":"2025-09-21T00:00:00+00:00","math":"2000-01-01T00:00:00+00:00","tool_use":null,"multilingual":"2000-01-01T00:00:00+00:00","hallucination":"2000-01-01T00:00:00+00:00","computer_use":null,"long_context":null,"coding":"2000-01-01T00:00:00+00:00","reasoning":"2025-09-21T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","json":null,"multimodal":null,"agentic":null,"instruction_following":null},"confidence":{"uncensored":0.2,"math":0.0,"tool_use":0.0,"multilingual":0.0,"hallucination":0.47,"computer_use":0.0,"long_context":0.0,"coding":0.0,"reasoning":0.0,"writing":0.18,"overall":0.21,"eq":0.0,"json":0.0,"multimodal":0.0,"agentic":0.0,"instruction_following":0.0},"sourceCounts":{"uncensored":4,"math":1,"tool_use":0,"multilingual":1,"hallucination":1,"computer_use":0,"long_context":0,"coding":1,"reasoning":1,"writing":2,"overall":1,"eq":1,"json":0,"multimodal":0,"agentic":0,"instruction_following":0},"inputCostPerMillion":0.45499999999999996,"outputCostPerMillion":1.8199999999999998,"contextWindowTokens":131072,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":32,"variantId":284,"modelSlug":"google--gemini-2.0-flash-001","modelName":"Google: Gemini 2.0 Flash","providerSlug":"google","providerName":"Google","modelFamily":null,"openWeights":false,"overallScore":65.5,"overallConfidence":0.17,"overallSourceCount":2,"scores":{"multilingual":null,"agentic":null,"eq":null,"uncensored":null,"computer_use":null,"reasoning":68.5,"coding":40.5,"json":null,"math":83.1,"overall":65.5,"writing":57.4,"instruction_following":null,"multimodal":69.2,"tool_use":null,"hallucination":null,"long_context":null},"freshness":{"multilingual":null,"agentic":"2025-08-17T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","uncensored":null,"computer_use":null,"reasoning":"2025-05-01T00:00:00+00:00","coding":"2026-05-20T12:15:25.845237+00:00","json":null,"math":"2025-05-01T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","instruction_following":null,"multimodal":"2000-01-01T00:00:00+00:00","tool_use":null,"hallucination":null,"long_context":null},"confidence":{"multilingual":0.0,"agentic":0.0,"eq":0.0,"uncensored":0.0,"computer_use":0.0,"reasoning":0.09,"coding":0.09,"json":0.0,"math":0.13,"overall":0.17,"writing":0.23,"instruction_following":0.0,"multimodal":0.24,"tool_use":0.0,"hallucination":0.0,"long_context":0.0},"sourceCounts":{"multilingual":0,"agentic":1,"eq":2,"uncensored":0,"computer_use":0,"reasoning":2,"coding":3,"json":0,"math":2,"overall":2,"writing":2,"instruction_following":0,"multimodal":1,"tool_use":0,"hallucination":0,"long_context":0},"inputCostPerMillion":0.09999999999999999,"outputCostPerMillion":0.39999999999999997,"contextWindowTokens":1048576,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Math"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":33,"variantId":273,"modelSlug":"google--gemma-3-27b-it","modelName":"Google: Gemma 3 27B","providerSlug":"google","providerName":"Google","modelFamily":null,"openWeights":false,"overallScore":65.2,"overallConfidence":0.17,"overallSourceCount":2,"scores":{"long_context":null,"agentic":null,"json":42.5,"overall":65.2,"multilingual":null,"computer_use":null,"coding":null,"math":null,"instruction_following":null,"eq":null,"reasoning":60.1,"tool_use":null,"hallucination":91.6,"uncensored":26.8,"writing":57.0,"multimodal":63.4},"freshness":{"long_context":null,"agentic":null,"json":"2026-05-15T17:27:34.392962+00:00","overall":"2026-08-27T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","computer_use":null,"coding":"2026-05-20T12:15:25.846417+00:00","math":"2025-05-01T00:00:00+00:00","instruction_following":null,"eq":"2000-01-01T00:00:00+00:00","reasoning":"2026-05-15T17:28:02.765101+00:00","tool_use":null,"hallucination":"2000-01-01T00:00:00+00:00","uncensored":"2025-09-06T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","multimodal":"2026-05-15T17:28:02.765101+00:00"},"confidence":{"long_context":0.0,"agentic":0.0,"json":0.21,"overall":0.17,"multilingual":0.0,"computer_use":0.0,"coding":0.0,"math":0.0,"instruction_following":0.0,"eq":0.0,"reasoning":0.06,"tool_use":0.0,"hallucination":0.47,"uncensored":0.2,"writing":0.17,"multimodal":0.26},"sourceCounts":{"long_context":0,"agentic":0,"json":4,"overall":2,"multilingual":1,"computer_use":0,"coding":1,"math":1,"instruction_following":0,"eq":2,"reasoning":3,"tool_use":0,"hallucination":1,"uncensored":4,"writing":3,"multimodal":1},"inputCostPerMillion":0.08,"outputCostPerMillion":0.44999999999999996,"contextWindowTokens":131072,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality"],"avoidFor":["Uncensored"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":34,"variantId":59,"modelSlug":"mistralai--mistral-small-2603","modelName":"Mistral: Mistral Small 4","providerSlug":"mistralai","providerName":"Mistralai","modelFamily":null,"openWeights":false,"overallScore":60.7,"overallConfidence":0.15,"overallSourceCount":3,"scores":{"math":null,"long_context":null,"computer_use":null,"overall":60.7,"tool_use":null,"eq":null,"agentic":null,"uncensored":null,"hallucination":null,"multilingual":null,"multimodal":null,"instruction_following":null,"reasoning":null,"json":45.9,"writing":54.2,"coding":31.9},"freshness":{"math":"2026-05-08T17:00:35.652912+00:00","long_context":null,"computer_use":null,"overall":"2026-08-27T00:00:00+00:00","tool_use":null,"eq":"2000-01-01T00:00:00+00:00","agentic":null,"uncensored":null,"hallucination":null,"multilingual":null,"multimodal":null,"instruction_following":"2026-05-08T17:00:35.652905+00:00","reasoning":"2026-05-08T17:00:35.652909+00:00","json":"2026-05-15T17:27:34.392962+00:00","writing":"2026-08-27T00:00:00+00:00","coding":"2026-05-20T12:15:25.851143+00:00"},"confidence":{"math":0.0,"long_context":0.0,"computer_use":0.0,"overall":0.15,"tool_use":0.0,"eq":0.0,"agentic":0.0,"uncensored":0.0,"hallucination":0.0,"multilingual":0.0,"multimodal":0.0,"instruction_following":0.0,"reasoning":0.0,"json":0.21,"writing":0.23,"coding":0.06},"sourceCounts":{"math":2,"long_context":0,"computer_use":0,"overall":3,"tool_use":0,"eq":1,"agentic":0,"uncensored":0,"hallucination":0,"multilingual":0,"multimodal":0,"instruction_following":1,"reasoning":2,"json":4,"writing":2,"coding":3},"inputCostPerMillion":0.15,"outputCostPerMillion":0.6,"contextWindowTokens":262144,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":[],"avoidFor":["Coding"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":35,"variantId":308,"modelSlug":"meta-llama--llama-3.3-70b-instruct","modelName":"Meta: Llama 3.3 70B Instruct","providerSlug":"meta-llama","providerName":"Meta Llama","modelFamily":null,"openWeights":false,"overallScore":59.1,"overallConfidence":0.14,"overallSourceCount":4,"scores":{"math":63.6,"reasoning":60.2,"tool_use":null,"instruction_following":null,"json":46.7,"computer_use":null,"long_context":null,"multimodal":null,"coding":38.2,"agentic":null,"uncensored":35.4,"writing":44.1,"hallucination":94.9,"multilingual":81.0,"overall":59.1,"eq":null},"freshness":{"math":"2026-05-08T17:00:35.652547+00:00","reasoning":"2026-05-08T17:00:35.652544+00:00","tool_use":null,"instruction_following":"2026-05-08T17:00:35.652540+00:00","json":"2026-05-15T17:27:34.392962+00:00","computer_use":null,"long_context":null,"multimodal":null,"coding":"2026-05-20T12:15:25.849857+00:00","agentic":null,"uncensored":"2025-09-10T00:00:00+00:00","writing":"2026-08-27T00:00:00+00:00","hallucination":"2000-01-01T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","overall":"2026-08-27T00:00:00+00:00","eq":null},"confidence":{"math":0.13,"reasoning":0.05,"tool_use":0.0,"instruction_following":0.0,"json":0.21,"computer_use":0.0,"long_context":0.0,"multimodal":0.0,"coding":0.07,"agentic":0.0,"uncensored":0.2,"writing":0.17,"hallucination":0.47,"multilingual":0.22,"overall":0.14,"eq":0.0},"sourceCounts":{"math":3,"reasoning":3,"tool_use":0,"instruction_following":1,"json":4,"computer_use":0,"long_context":0,"multimodal":0,"coding":4,"agentic":0,"uncensored":4,"writing":4,"hallucination":1,"multilingual":2,"overall":4,"eq":0},"inputCostPerMillion":0.71,"outputCostPerMillion":0.71,"contextWindowTokens":131072,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality","Multilingual"],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":36,"variantId":251,"modelSlug":"qwen--qwen3-32b","modelName":"Qwen: Qwen3 32B","providerSlug":"qwen","providerName":"Qwen","modelFamily":null,"openWeights":false,"overallScore":58.7,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"uncensored":30.5,"overall":58.7,"eq":null,"multilingual":null,"writing":56.9,"tool_use":null,"instruction_following":null,"json":null,"computer_use":null,"hallucination":93.1,"agentic":null,"long_context":null,"multimodal":null,"reasoning":null,"coding":null,"math":null},"freshness":{"uncensored":"2025-09-13T00:00:00+00:00","overall":"2026-08-27T00:00:00+00:00","eq":"2000-01-01T00:00:00+00:00","multilingual":null,"writing":"2026-08-27T00:00:00+00:00","tool_use":null,"instruction_following":null,"json":null,"computer_use":null,"hallucination":"2000-01-01T00:00:00+00:00","agentic":"2025-06-19T00:00:00+00:00","long_context":null,"multimodal":null,"reasoning":"2025-09-13T00:00:00+00:00","coding":"2000-01-01T00:00:00+00:00","math":null},"confidence":{"uncensored":0.2,"overall":0.21,"eq":0.0,"multilingual":0.0,"writing":0.18,"tool_use":0.0,"instruction_following":0.0,"json":0.0,"computer_use":0.0,"hallucination":0.47,"agentic":0.0,"long_context":0.0,"multimodal":0.0,"reasoning":0.0,"coding":0.0,"math":0.0},"sourceCounts":{"uncensored":4,"overall":1,"eq":1,"multilingual":0,"writing":2,"tool_use":0,"instruction_following":0,"json":0,"computer_use":0,"hallucination":1,"agentic":1,"long_context":0,"multimodal":0,"reasoning":1,"coding":1,"math":0},"inputCostPerMillion":0.08,"outputCostPerMillion":0.28,"contextWindowTokens":131072,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":["Factuality"],"avoidFor":["Uncensored"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":37,"variantId":339,"modelSlug":"mistralai--mistral-nemo","modelName":"Mistral: Mistral Nemo","providerSlug":"mistralai","providerName":"Mistralai","modelFamily":null,"openWeights":false,"overallScore":55.8,"overallConfidence":0.11,"overallSourceCount":1,"scores":{"uncensored":36.2,"long_context":null,"eq":null,"math":null,"reasoning":40.2,"writing":null,"tool_use":null,"instruction_following":null,"json":null,"overall":55.8,"multilingual":null,"multimodal":null,"coding":null,"hallucination":null,"computer_use":null,"agentic":null},"freshness":{"uncensored":"2025-09-06T00:00:00+00:00","long_context":null,"eq":null,"math":"2026-05-08T17:00:35.652855+00:00","reasoning":"2026-05-08T17:00:35.652852+00:00","writing":"2025-09-06T00:00:00+00:00","tool_use":null,"instruction_following":"2026-05-08T17:00:35.652848+00:00","json":null,"overall":"2026-05-08T17:00:35.652848+00:00","multilingual":"2026-07-28T12:18:16+00:00","multimodal":null,"coding":null,"hallucination":null,"computer_use":null,"agentic":null},"confidence":{"uncensored":0.2,"long_context":0.0,"eq":0.0,"math":0.0,"reasoning":0.05,"writing":0.0,"tool_use":0.0,"instruction_following":0.0,"json":0.0,"overall":0.11,"multilingual":0.0,"multimodal":0.0,"coding":0.0,"hallucination":0.0,"computer_use":0.0,"agentic":0.0},"sourceCounts":{"uncensored":4,"long_context":0,"eq":0,"math":2,"reasoning":3,"writing":1,"tool_use":0,"instruction_following":1,"json":0,"overall":1,"multilingual":1,"multimodal":0,"coding":0,"hallucination":0,"computer_use":0,"agentic":0},"inputCostPerMillion":0.019000000000000003,"outputCostPerMillion":0.03,"contextWindowTokens":131072,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":[],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-05-08T17:00:35.652848+00:00","hasRealData":true},{"rank":38,"variantId":248,"modelSlug":"qwen--qwen3-30b-a3b","modelName":"Qwen: Qwen3 30B A3B","providerSlug":"qwen","providerName":"Qwen","modelFamily":null,"openWeights":false,"overallScore":53.7,"overallConfidence":0.21,"overallSourceCount":1,"scores":{"long_context":null,"hallucination":null,"eq":null,"tool_use":null,"json":null,"coding":null,"instruction_following":null,"uncensored":32.1,"multilingual":null,"computer_use":null,"overall":53.7,"multimodal":null,"agentic":null,"writing":52.2,"math":null,"reasoning":null},"freshness":{"long_context":null,"hallucination":null,"eq":"2000-01-01T00:00:00+00:00","tool_use":null,"json":null,"coding":"2000-01-01T00:00:00+00:00","instruction_following":null,"uncensored":"2025-11-08T00:00:00+00:00","multilingual":"2026-07-28T12:18:16+00:00","computer_use":null,"overall":"2026-08-27T00:00:00+00:00","multimodal":null,"agentic":null,"writing":"2026-08-27T00:00:00+00:00","math":null,"reasoning":"2025-11-08T00:00:00+00:00"},"confidence":{"long_context":0.0,"hallucination":0.0,"eq":0.0,"tool_use":0.0,"json":0.0,"coding":0.0,"instruction_following":0.0,"uncensored":0.2,"multilingual":0.0,"computer_use":0.0,"overall":0.21,"multimodal":0.0,"agentic":0.0,"writing":0.18,"math":0.0,"reasoning":0.0},"sourceCounts":{"long_context":0,"hallucination":0,"eq":1,"tool_use":0,"json":0,"coding":1,"instruction_following":0,"uncensored":4,"multilingual":1,"computer_use":0,"overall":1,"multimodal":0,"agentic":0,"writing":2,"math":0,"reasoning":1},"inputCostPerMillion":0.12,"outputCostPerMillion":0.5,"contextWindowTokens":131072,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":[],"avoidFor":["Uncensored"],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true},{"rank":39,"variantId":316,"modelSlug":"qwen--qwen-2.5-coder-32b-instruct","modelName":"Qwen2.5 Coder 32B Instruct","providerSlug":"qwen","providerName":"Qwen","modelFamily":null,"openWeights":false,"overallScore":46.2,"overallConfidence":0.17,"overallSourceCount":2,"scores":{"agentic":null,"computer_use":null,"long_context":null,"uncensored":null,"writing":39.1,"instruction_following":null,"multimodal":null,"overall":46.2,"tool_use":null,"hallucination":53.2,"eq":null,"reasoning":null,"multilingual":null,"coding":55.6,"math":null,"json":null},"freshness":{"agentic":null,"computer_use":null,"long_context":null,"uncensored":null,"writing":"2026-08-27T00:00:00+00:00","instruction_following":null,"multimodal":null,"overall":"2026-08-27T00:00:00+00:00","tool_use":null,"hallucination":"2000-01-01T00:00:00+00:00","eq":null,"reasoning":null,"multilingual":null,"coding":"2026-05-20T12:15:25.836440+00:00","math":"2000-01-01T00:00:00+00:00","json":null},"confidence":{"agentic":0.0,"computer_use":0.0,"long_context":0.0,"uncensored":0.0,"writing":0.23,"instruction_following":0.0,"multimodal":0.0,"overall":0.17,"tool_use":0.0,"hallucination":0.16,"eq":0.0,"reasoning":0.0,"multilingual":0.0,"coding":0.06,"math":0.0,"json":0.0},"sourceCounts":{"agentic":0,"computer_use":0,"long_context":0,"uncensored":0,"writing":2,"instruction_following":0,"multimodal":0,"overall":2,"tool_use":0,"hallucination":1,"eq":0,"reasoning":0,"multilingual":0,"coding":6,"math":1,"json":0},"inputCostPerMillion":0.66,"outputCostPerMillion":1.0,"contextWindowTokens":32768,"medianLatencyMs":null,"outputTokensPerSecond":null,"bestFor":[],"avoidFor":[],"scoredAt":null,"lastUpdated":"2026-08-27T00:00:00+00:00","hasRealData":true}],"total":39,"filters":{"provider":null,"open_weights":null,"task":null,"price_tier":null},"sortBy":"overall","sortDir":"desc","publicationStatus":null}