{"source":"AIMap","schema":"benchmark/v1","updated":"2026-10-22","benchmark":{"id":"aime","name":"AIME (OTIS Mock AIME 2024–2025)","category":"math","unit":"%","higherIsBetter":true,"status":"active","sources":["epoch"],"primaryVariant":"epoch","url":"https://epoch.ai/benchmarks/otis-mock-aime","year":2025,"desc":{"en":"AIME-style competition maths (integer answers 0–999). We use Epoch AI's runs on the OTIS Mock AIME 2024–2025 papers, which are less exposed than past official AIME papers.","zh-hans":"AIME 风格的竞赛数学（答案为 0–999 的整数）。本站使用 Epoch AI 在 OTIS 模拟 AIME 2024–2025 试卷上的评测，比历年 AIME 真题暴露更少。"},"measures":{"en":"Accuracy, averaged over runs.","zh-hans":"多次运行的平均准确率。"},"limits":{"en":"Few questions, so results are noisy. Vendor 'AIME 2025' claims in launch posts are not comparable with these numbers.","zh-hans":"题量少，结果波动大。厂商发布会上的“AIME 2025”成绩与这里不可直接比较。"},"contamination":"medium","contaminationNote":{"en":"Mock papers are public after release.","zh-hans":"模拟卷发布后即公开。"},"stats":{"results":265,"models":200,"latest":"2026-10-19","bySourceType":{"independent":265}}},"sources":[{"id":"epoch","name":"Epoch AI Benchmarking Hub","license":"CC BY 4.0","policy":"open","attribution":"Epoch AI, 'Capabilities & benchmarking', https://epoch.ai/benchmarks (CC BY 4.0)","site":"https://epoch.ai/benchmarks"}],"results":[{"model":"gemini-4-argon","modelName":"Gemini 4 Argon","provider":"Google","rawName":"Gemini 4 Argon","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-10-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-22"},{"model":"gpt-6-1-sol","modelName":"GPT-6.1 Sol","provider":"OpenAI","rawName":"GPT-6.1 Sol","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-09-29","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-5-5","modelName":"Claude Sonnet 5.5","provider":"Anthropic","rawName":"Claude Sonnet 5.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-09-29","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-6-sol","modelName":"GPT-6 Sol","provider":"OpenAI","rawName":"GPT-6 Sol","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-09-22","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-5-5","modelName":"Claude Opus 5.5","provider":"Anthropic","rawName":"Claude Opus 5.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-09-22","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-8-max-0902","modelName":"Qwen3.8 Max (0902)","provider":"Alibaba (Qwen)","rawName":"Qwen3.8 Max (0902)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-09-02","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-fable-5-1","modelName":"Claude Fable 5.1","provider":"Anthropic","rawName":"Claude Fable 5.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-09-01","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-6-astra","modelName":"GPT-6 Astra","provider":"OpenAI","rawName":"GPT-6 Astra","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-fable-5","modelName":"Claude Fable 5","provider":"Anthropic","rawName":"Claude Fable 5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-sol","modelName":"GPT-5.6 Sol","provider":"OpenAI","rawName":"GPT-5.6 Sol","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-07-09","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-5-pro","modelName":"GPT-5.5 Pro","provider":"OpenAI","rawName":"GPT-5.5 Pro","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-04-24","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-5","modelName":"GPT-5.5","provider":"OpenAI","rawName":"GPT-5.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":100,"unit":"%","rank":1,"rankComputedBySite":true,"date":"2026-04-24","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-terra","modelName":"GPT-5.6 Terra","provider":"OpenAI","rawName":"GPT-5.6 Terra","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":99.72,"unit":"%","rank":13,"rankComputedBySite":true,"date":"2026-07-09","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-fable-5","modelName":"Claude Fable 5","provider":"Anthropic","rawName":"Claude Fable 5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":99.72,"unit":"%","rank":13,"rankComputedBySite":true,"date":"2026-06-10","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v4-1-flash-1017","modelName":"DeepSeek V4.1 Flash 1017","provider":"DeepSeek","rawName":"DeepSeek V4.1 Flash 1017","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":99.44,"unit":"%","rank":15,"rankComputedBySite":true,"date":"2026-10-19","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-22"},{"model":"muse-wonder","modelName":"Muse Wonder","provider":"Meta","rawName":"Muse Wonder","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":99.44,"unit":"%","rank":15,"rankComputedBySite":true,"date":"2026-10-12","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-22"},{"model":"qwen-3-8-max","modelName":"Qwen 3.8 Max","provider":"Alibaba (Qwen)","rawName":"Qwen 3.8 Max","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":99.44,"unit":"%","rank":15,"rankComputedBySite":true,"date":"2026-08-04","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"muse-spark-1-3","modelName":"Muse Spark 1.3","provider":"Meta","rawName":"Muse Spark 1.3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":99.17,"unit":"%","rank":18,"rankComputedBySite":true,"date":"2026-09-17","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-4-6","modelName":"Grok 4.6","provider":"xAI","rawName":"Grok 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":99.17,"unit":"%","rank":18,"rankComputedBySite":true,"date":"2026-08-14","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-haiku-5-5","modelName":"Claude Haiku 5.5","provider":"Anthropic","rawName":"Claude Haiku 5.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":98.89,"unit":"%","rank":20,"rankComputedBySite":true,"date":"2026-10-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-6-luna","modelName":"GPT-6 Luna","provider":"OpenAI","rawName":"GPT-6 Luna","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":98.89,"unit":"%","rank":20,"rankComputedBySite":true,"date":"2026-09-22","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-8-flash","modelName":"Gemini 3.8 Flash","provider":"Google","rawName":"Gemini 3.8 Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":98.89,"unit":"%","rank":20,"rankComputedBySite":true,"date":"2026-09-02","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-5","modelName":"Claude Opus 5","provider":"Anthropic","rawName":"Claude Opus 5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":98.89,"unit":"%","rank":20,"rankComputedBySite":true,"date":"2026-07-24","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v4-pro-0813","modelName":"DeepSeek V4 Pro 0813","provider":"DeepSeek","rawName":"DeepSeek V4 Pro 0813","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":98.61,"unit":"%","rank":24,"rankComputedBySite":true,"date":"2026-08-18","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-large-4","modelName":"Mistral Large 4","provider":"Mistral AI","rawName":"Mistral Large 4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":98.33,"unit":"%","rank":25,"rankComputedBySite":true,"date":"2026-10-12","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-22"},{"model":"deepseek-v4-1-flash","modelName":"DeepSeek V4.1 Flash","provider":"DeepSeek","rawName":"DeepSeek V4.1 Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":98.33,"unit":"%","rank":25,"rankComputedBySite":true,"date":"2026-10-08","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-luna","modelName":"GPT-5.6 Luna","provider":"OpenAI","rawName":"GPT-5.6 Luna","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":98.33,"unit":"%","rank":25,"rankComputedBySite":true,"date":"2026-07-09","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"muse-spark-open","modelName":"Muse Spark Open","provider":"Meta","rawName":"Muse Spark Open","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":98.06,"unit":"%","rank":28,"rankComputedBySite":true,"date":"2026-10-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-22"},{"model":"grok-4-7","modelName":"Grok 4.7","provider":"xAI","rawName":"Grok 4.7","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":98.06,"unit":"%","rank":28,"rankComputedBySite":true,"date":"2026-09-22","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-7","modelName":"Claude Opus 4.7","provider":"Anthropic","rawName":"Claude Opus 4.7","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":97.8,"unit":"%","rank":30,"rankComputedBySite":true,"date":"2026-04-17","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-4-6","modelName":"Grok 4.6","provider":"xAI","rawName":"Grok 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":97.78,"unit":"%","rank":31,"rankComputedBySite":true,"date":"2026-08-12","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-5","modelName":"Claude Opus 5","provider":"Anthropic","rawName":"Claude Opus 5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":97.78,"unit":"%","rank":31,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-fable-5","modelName":"Claude Fable 5","provider":"Anthropic","rawName":"Claude Fable 5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":97.78,"unit":"%","rank":31,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4","modelName":"GPT-5.4","provider":"OpenAI","rawName":"GPT-5.4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":97.78,"unit":"%","rank":31,"rankComputedBySite":true,"date":"2026-07-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-4-5","modelName":"Grok 4.5","provider":"xAI","rawName":"Grok 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":97.78,"unit":"%","rank":31,"rankComputedBySite":true,"date":"2026-07-08","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-haiku-5-5","modelName":"Claude Haiku 5.5","provider":"Anthropic","rawName":"Claude Haiku 5.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":97.22,"unit":"%","rank":36,"rankComputedBySite":true,"date":"2026-10-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-7-flash","modelName":"Gemini 3.7 Flash","provider":"Google","rawName":"Gemini 3.7 Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":97.22,"unit":"%","rank":36,"rankComputedBySite":true,"date":"2026-08-14","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"kimi-k3","modelName":"Kimi K3","provider":"Moonshot AI","rawName":"Kimi K3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":97.22,"unit":"%","rank":36,"rankComputedBySite":true,"date":"2026-07-16","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v4-pro","modelName":"DeepSeek-V4-Pro","provider":"DeepSeek","rawName":"DeepSeek-V4-Pro","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":96.67,"unit":"%","rank":39,"rankComputedBySite":true,"date":"2026-06-17","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"kimi-k2-6","modelName":"Kimi K2.6","provider":"Moonshot AI","rawName":"Kimi K2.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":96.11,"unit":"%","rank":40,"rankComputedBySite":true,"date":"2026-05-02","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-2","modelName":"GPT-5.2","provider":"OpenAI","rawName":"GPT-5.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":96.11,"unit":"%","rank":40,"rankComputedBySite":true,"date":"2025-12-11","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-2","modelName":"GPT-5.2","provider":"OpenAI","rawName":"GPT-5.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":96.1,"unit":"%","rank":42,"rankComputedBySite":true,"date":"2025-12-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-sol","modelName":"GPT-5.6 Sol","provider":"OpenAI","rawName":"GPT-5.6 Sol","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":95.56,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-7-max","modelName":"Qwen3.7-Max","provider":"Alibaba (Qwen)","rawName":"Qwen3.7-Max","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":95.56,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"kimi-k2-7-code","modelName":"Kimi K2.7 Code","provider":"Moonshot AI","rawName":"Kimi K2.7 Code","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":95.56,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-1-pro","modelName":"Gemini 3.1 Pro","provider":"Google","rawName":"Gemini 3.1 Pro","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":95.56,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v4-pro","modelName":"DeepSeek-V4-Pro","provider":"DeepSeek","rawName":"DeepSeek-V4-Pro","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":95.56,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-flash","modelName":"Gemini 3 Flash","provider":"Google","rawName":"Gemini 3 Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":95.56,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4","modelName":"GPT-5.4","provider":"OpenAI","rawName":"GPT-5.4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":95.56,"unit":"%","rank":43,"rankComputedBySite":true,"date":"2026-07-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4","modelName":"GPT-5.4","provider":"OpenAI","rawName":"GPT-5.4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":95.3,"unit":"%","rank":50,"rankComputedBySite":true,"date":"2026-03-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-5","modelName":"Claude Sonnet 5","provider":"Anthropic","rawName":"Claude Sonnet 5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":94.72,"unit":"%","rank":51,"rankComputedBySite":true,"date":"2026-07-01","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v4-flash-0731","modelName":"DeepSeek V4 Flash 0731","provider":"DeepSeek","rawName":"DeepSeek V4 Flash 0731","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":94.44,"unit":"%","rank":52,"rankComputedBySite":true,"date":"2026-08-02","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-6","modelName":"Claude Opus 4.6","provider":"Anthropic","rawName":"Claude Opus 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 64k thinking","score":94.44,"unit":"%","rank":52,"rankComputedBySite":true,"date":"2026-02-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"glm-5-3-flash","modelName":"GLM-5.3-Flash","provider":"Zhipu AI (Z.ai)","rawName":"GLM-5.3-Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":93.89,"unit":"%","rank":54,"rankComputedBySite":true,"date":"2026-08-26","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-2","modelName":"GPT-5.2","provider":"OpenAI","rawName":"GPT-5.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":93.89,"unit":"%","rank":54,"rankComputedBySite":true,"date":"2025-12-11","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"glm-5-1","modelName":"GLM-5.1","provider":"Zhipu AI (Z.ai)","rawName":"GLM-5.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":93.33,"unit":"%","rank":56,"rankComputedBySite":true,"date":"2026-08-10","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"kimi-k3","modelName":"Kimi K3","provider":"Moonshot AI","rawName":"Kimi K3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":93.33,"unit":"%","rank":56,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen-3-6-plus","modelName":"Qwen 3.6 Plus","provider":"Alibaba (Qwen)","rawName":"Qwen 3.6 Plus","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 2026-04-02","score":93.33,"unit":"%","rank":56,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-7-plus","modelName":"Qwen3.7-Plus","provider":"Alibaba (Qwen)","rawName":"Qwen3.7-Plus","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":93.33,"unit":"%","rank":56,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-5","modelName":"Claude Opus 5","provider":"Anthropic","rawName":"Claude Opus 5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":93.33,"unit":"%","rank":56,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-4-3-beta","modelName":"Grok 4.3 Beta","provider":"xAI","rawName":"Grok 4.3 Beta","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":93.33,"unit":"%","rank":56,"rankComputedBySite":true,"date":"2026-06-17","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-6","modelName":"Claude Opus 4.6","provider":"Anthropic","rawName":"Claude Opus 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 32k thinking","score":93.06,"unit":"%","rank":62,"rankComputedBySite":true,"date":"2026-02-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-4-20","modelName":"Grok 4.20","provider":"xAI","rawName":"Grok 4.20","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":92.22,"unit":"%","rank":63,"rankComputedBySite":true,"date":"2026-07-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"kimi-k2-5","modelName":"Kimi K2.5","provider":"Moonshot AI","rawName":"Kimi K2.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Fireworks","score":92.2,"unit":"%","rank":64,"rankComputedBySite":true,"date":"2026-02-02","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-pro","modelName":"Gemini 3 Pro","provider":"Google","rawName":"Gemini 3 Pro","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":91.39,"unit":"%","rank":65,"rankComputedBySite":true,"date":"2025-11-19","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5","modelName":"GPT-5","provider":"OpenAI","rawName":"GPT-5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":91.39,"unit":"%","rank":65,"rankComputedBySite":true,"date":"2025-10-29","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"glm-5-3","modelName":"GLM-5.3","provider":"Zhipu AI (Z.ai)","rawName":"GLM-5.3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":91.11,"unit":"%","rank":67,"rankComputedBySite":true,"date":"2026-08-24","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen-3-6-max-preview","modelName":"Qwen 3.6 Max (Preview)","provider":"Alibaba (Qwen)","rawName":"Qwen 3.6 Max (Preview)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Preview","score":91.11,"unit":"%","rank":67,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-6-27b","modelName":"Qwen3.6 27B","provider":"Alibaba (Qwen)","rawName":"Qwen3.6 27B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":91.11,"unit":"%","rank":67,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-6","modelName":"Claude Opus 4.6","provider":"Anthropic","rawName":"Claude Opus 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":91.11,"unit":"%","rank":67,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"inkling-small","modelName":"Inkling-Small","provider":"Thinking Machines","rawName":"Inkling-Small","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":90,"unit":"%","rank":71,"rankComputedBySite":true,"date":"2026-08-14","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"muse-spark","modelName":"Muse Spark","provider":"Meta","rawName":"Muse Spark","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":88.9,"unit":"%","rank":72,"rankComputedBySite":true,"date":"2026-04-08","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4-mini","modelName":"GPT-5.4 Mini","provider":"OpenAI","rawName":"GPT-5.4 Mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":88.89,"unit":"%","rank":73,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-terra","modelName":"GPT-5.6 Terra","provider":"OpenAI","rawName":"GPT-5.6 Terra","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":88.89,"unit":"%","rank":73,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-5-397b-a17b","modelName":"Qwen3.5 397B-A17B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5 397B-A17B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":88.89,"unit":"%","rank":73,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-5-flash","modelName":"Gemini 3.5 Flash","provider":"Google","rawName":"Gemini 3.5 Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":88.89,"unit":"%","rank":73,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"inkling","modelName":"Inkling","provider":"Thinking Machines","rawName":"Inkling","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh","score":88.89,"unit":"%","rank":73,"rankComputedBySite":true,"date":"2026-08-05","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-oss-120b","modelName":"gpt-oss-120b","provider":"OpenAI","rawName":"gpt-oss-120b","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":88.89,"unit":"%","rank":73,"rankComputedBySite":true,"date":"2025-12-11","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-1","modelName":"GPT-5.1","provider":"OpenAI","rawName":"GPT-5.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":88.61,"unit":"%","rank":79,"rankComputedBySite":true,"date":"2025-11-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v3-2","modelName":"DeepSeek-V3.2","provider":"DeepSeek","rawName":"DeepSeek-V3.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Thinking","score":87.82,"unit":"%","rank":80,"rankComputedBySite":true,"date":"2025-12-16","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4-nano","modelName":"GPT-5.4 Nano","provider":"OpenAI","rawName":"GPT-5.4 Nano","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":87.78,"unit":"%","rank":81,"rankComputedBySite":true,"date":"2026-04-14","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4-mini","modelName":"GPT-5.4 Mini","provider":"OpenAI","rawName":"GPT-5.4 Mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":87.22,"unit":"%","rank":82,"rankComputedBySite":true,"date":"2026-04-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5","modelName":"GPT-5","provider":"OpenAI","rawName":"GPT-5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":87.22,"unit":"%","rank":82,"rankComputedBySite":true,"date":"2025-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"nemotron-3-ultra","modelName":"Nemotron 3 Ultra","provider":"NVIDIA","rawName":"Nemotron 3 Ultra","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":86.67,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2026-08-10","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen-3-5-plus-hosted-397b-a17b","modelName":"Qwen 3.5 Plus (hosted 397B-A17B)","provider":"Alibaba (Qwen)","rawName":"Qwen 3.5 Plus (hosted 397B-A17B)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":86.67,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen-3-6-35b-a3b","modelName":"Qwen 3.6 35B-A3B","provider":"Alibaba (Qwen)","rawName":"Qwen 3.6 35B-A3B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":86.67,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-7-flash","modelName":"Qwen3.7 Flash","provider":"Alibaba (Qwen)","rawName":"Qwen3.7 Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":86.67,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-7","modelName":"Claude Opus 4.7","provider":"Anthropic","rawName":"Claude Opus 4.7","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":86.67,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-235b-a22b-thinking-jul-2025","modelName":"Qwen3-235B-A22B-Thinking (Jul 2025)","provider":"Alibaba (Qwen)","rawName":"Qwen3-235B-A22B-Thinking (Jul 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":86.67,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2025-12-10","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-mini","modelName":"GPT-5 mini","provider":"OpenAI","rawName":"GPT-5 mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":86.67,"unit":"%","rank":84,"rankComputedBySite":true,"date":"2025-10-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-5","modelName":"Claude Opus 4.5","provider":"Anthropic","rawName":"Claude Opus 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 32k thinking","score":86.11,"unit":"%","rank":91,"rankComputedBySite":true,"date":"2025-11-24","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4-6","modelName":"Claude Sonnet 4.6","provider":"Anthropic","rawName":"Claude Sonnet 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 32k thinking","score":85.79,"unit":"%","rank":92,"rankComputedBySite":true,"date":"2026-02-20","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-1","modelName":"GPT-5.1","provider":"OpenAI","rawName":"GPT-5.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":85.56,"unit":"%","rank":93,"rankComputedBySite":true,"date":"2025-11-17","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-2-5-pro-jun-2025","modelName":"Gemini 2.5 Pro (Jun 2025)","provider":"Google","rawName":"Gemini 2.5 Pro (Jun 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":84.72,"unit":"%","rank":94,"rankComputedBySite":true,"date":"2025-11-16","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-5","modelName":"GPT-5.5","provider":"OpenAI","rawName":"GPT-5.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":84.44,"unit":"%","rank":95,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o3","modelName":"o3","provider":"OpenAI","rawName":"o3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":84.44,"unit":"%","rank":95,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen-3-6-flash","modelName":"Qwen 3.6 Flash","provider":"Alibaba (Qwen)","rawName":"Qwen 3.6 Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 2026-04-16","score":84.44,"unit":"%","rank":95,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen-3-5-flash-hosted-35b-a3b","modelName":"Qwen 3.5 Flash (hosted 35B-A3B)","provider":"Alibaba (Qwen)","rawName":"Qwen 3.5 Flash (hosted 35B-A3B)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":84.44,"unit":"%","rank":95,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-8","modelName":"Claude Opus 4.8","provider":"Anthropic","rawName":"Claude Opus 4.8","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":84.44,"unit":"%","rank":95,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4","modelName":"GPT-5.4","provider":"OpenAI","rawName":"GPT-5.4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":84.44,"unit":"%","rank":95,"rankComputedBySite":true,"date":"2026-07-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-4","modelName":"Grok 4","provider":"xAI","rawName":"Grok 4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":84,"unit":"%","rank":101,"rankComputedBySite":true,"date":"2025-07-09","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o3","modelName":"o3","provider":"OpenAI","rawName":"o3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":83.89,"unit":"%","rank":102,"rankComputedBySite":true,"date":"2025-04-16","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"glm-4-7","modelName":"GLM-4.7","provider":"Zhipu AI (Z.ai)","rawName":"GLM-4.7","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":83.33,"unit":"%","rank":103,"rankComputedBySite":true,"date":"2026-01-29","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"kimi-k2","modelName":"Kimi K2 Thinking","provider":"Moonshot AI","rawName":"Kimi K2 Thinking","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":83.06,"unit":"%","rank":104,"rankComputedBySite":true,"date":"2025-11-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemma-4-26b-a4b","modelName":"Gemma 4 26B A4B","provider":"Google","rawName":"Gemma 4 26B A4B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":82.22,"unit":"%","rank":105,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4-6","modelName":"Claude Sonnet 4.6","provider":"Anthropic","rawName":"Claude Sonnet 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":82.22,"unit":"%","rank":105,"rankComputedBySite":true,"date":"2026-07-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-5","modelName":"Claude Opus 4.5","provider":"Anthropic","rawName":"Claude Opus 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 16k thinking","score":81.67,"unit":"%","rank":107,"rankComputedBySite":true,"date":"2025-11-24","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o4-mini","modelName":"o4-mini","provider":"OpenAI","rawName":"o4-mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":81.67,"unit":"%","rank":107,"rankComputedBySite":true,"date":"2025-04-16","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-nano","modelName":"GPT-5 nano","provider":"OpenAI","rawName":"GPT-5 nano","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":81.11,"unit":"%","rank":109,"rankComputedBySite":true,"date":"2025-10-31","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-6-flash","modelName":"Gemini 3.6 Flash","provider":"Google","rawName":"Gemini 3.6 Flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":80,"unit":"%","rank":110,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-5","modelName":"Claude Sonnet 5","provider":"Anthropic","rawName":"Claude Sonnet 5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":80,"unit":"%","rank":110,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"glm-5","modelName":"GLM-5","provider":"Zhipu AI (Z.ai)","rawName":"GLM-5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":80,"unit":"%","rank":110,"rankComputedBySite":true,"date":"2026-02-12","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-2","modelName":"GPT-5.2","provider":"OpenAI","rawName":"GPT-5.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":78.89,"unit":"%","rank":113,"rankComputedBySite":true,"date":"2025-12-11","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-mini","modelName":"GPT-5 mini","provider":"OpenAI","rawName":"GPT-5 mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":78.33,"unit":"%","rank":114,"rankComputedBySite":true,"date":"2025-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4-5","modelName":"Claude Sonnet 4.5","provider":"Anthropic","rawName":"Claude Sonnet 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 59k thinking","score":77.78,"unit":"%","rank":115,"rankComputedBySite":true,"date":"2025-10-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4-5","modelName":"Claude Sonnet 4.5","provider":"Anthropic","rawName":"Claude Sonnet 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 32k thinking","score":77.78,"unit":"%","rank":115,"rankComputedBySite":true,"date":"2025-10-21","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o3-mini","modelName":"o3-mini","provider":"OpenAI","rawName":"o3-mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":76.94,"unit":"%","rank":117,"rankComputedBySite":true,"date":"2025-02-27","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4-6","modelName":"Claude Sonnet 4.6","provider":"Anthropic","rawName":"Claude Sonnet 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":75.56,"unit":"%","rank":118,"rankComputedBySite":true,"date":"2026-07-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-nano","modelName":"GPT-5 nano","provider":"OpenAI","rawName":"GPT-5 nano","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":74.17,"unit":"%","rank":119,"rankComputedBySite":true,"date":"2025-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o4-mini","modelName":"o4-mini","provider":"OpenAI","rawName":"o4-mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":73.33,"unit":"%","rank":120,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemma-4-31b-it","modelName":"Gemma 4 31B IT","provider":"Google","rawName":"Gemma 4 31B IT","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":73.33,"unit":"%","rank":120,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o1","modelName":"o1","provider":"OpenAI","rawName":"o1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":73.33,"unit":"%","rank":120,"rankComputedBySite":true,"date":"2026-07-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-max","modelName":"Qwen3-Max","provider":"Alibaba (Qwen)","rawName":"Qwen3-Max","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":73.33,"unit":"%","rank":120,"rankComputedBySite":true,"date":"2025-10-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o1","modelName":"o1","provider":"OpenAI","rawName":"o1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":73.33,"unit":"%","rank":120,"rankComputedBySite":true,"date":"2025-02-27","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-2-5-flash-apr-2025","modelName":"Gemini 2.5 Flash (Apr 2025)","provider":"Google","rawName":"Gemini 2.5 Flash (Apr 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Apr 2025","score":73.06,"unit":"%","rank":125,"rankComputedBySite":true,"date":"2025-04-22","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4-6","modelName":"Claude Sonnet 4.6","provider":"Anthropic","rawName":"Claude Sonnet 4.6","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: max","score":71.11,"unit":"%","rank":126,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4-5","modelName":"Claude Sonnet 4.5","provider":"Anthropic","rawName":"Claude Sonnet 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 16k thinking","score":71.11,"unit":"%","rank":126,"rankComputedBySite":true,"date":"2025-10-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-2-5-flash-may-2025","modelName":"Gemini 2.5 Flash (May 2025)","provider":"Google","rawName":"Gemini 2.5 Flash (May 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":70.83,"unit":"%","rank":128,"rankComputedBySite":true,"date":"2025-05-20","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-30b-a3b-thinking-jul-2025","modelName":"Qwen3-30B-A3B-Thinking (Jul 2025)","provider":"Alibaba (Qwen)","rawName":"Qwen3-30B-A3B-Thinking (Jul 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":70.28,"unit":"%","rank":129,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-5-35b-a3b","modelName":"Qwen3.5-35B-A3B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-35B-A3B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":70,"unit":"%","rank":130,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-sol","modelName":"GPT-5.6 Sol","provider":"OpenAI","rawName":"GPT-5.6 Sol","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: none","score":68.89,"unit":"%","rank":131,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"kimi-k3","modelName":"Kimi K3","provider":"Moonshot AI","rawName":"Kimi K3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":68.89,"unit":"%","rank":131,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4-nano","modelName":"GPT-5.4 Nano","provider":"OpenAI","rawName":"GPT-5.4 Nano","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":68.89,"unit":"%","rank":131,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-1","modelName":"Claude Opus 4.1","provider":"Anthropic","rawName":"Claude Opus 4.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":68.89,"unit":"%","rank":131,"rankComputedBySite":true,"date":"2025-08-05","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4","modelName":"Claude Sonnet 4","provider":"Anthropic","rawName":"Claude Sonnet 4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":68.89,"unit":"%","rank":131,"rankComputedBySite":true,"date":"2025-05-23","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-5-instant","modelName":"GPT-5.5 Instant","provider":"OpenAI","rawName":"GPT-5.5 Instant","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":68.06,"unit":"%","rank":136,"rankComputedBySite":true,"date":"2026-08-02","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"seed-oss-36b-instruct","modelName":"seed-oss-36b-instruct","provider":"ByteDance","rawName":"seed-oss-36b-instruct","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":67.5,"unit":"%","rank":137,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-luna","modelName":"GPT-5.6 Luna","provider":"OpenAI","rawName":"GPT-5.6 Luna","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":66.67,"unit":"%","rank":138,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-haiku-4-5","modelName":"Claude Haiku 4.5","provider":"Anthropic","rawName":"Claude Haiku 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":66.67,"unit":"%","rank":138,"rankComputedBySite":true,"date":"2025-10-22","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-r1-may-2025","modelName":"DeepSeek-R1 (May 2025)","provider":"DeepSeek","rawName":"DeepSeek-R1 (May 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: May 2025","score":66.39,"unit":"%","rank":140,"rankComputedBySite":true,"date":"2025-05-29","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4","modelName":"Claude Opus 4","provider":"Anthropic","rawName":"Claude Opus 4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":64.44,"unit":"%","rank":141,"rankComputedBySite":true,"date":"2025-05-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-1","modelName":"GPT-5.1","provider":"OpenAI","rawName":"GPT-5.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":63.89,"unit":"%","rank":142,"rankComputedBySite":true,"date":"2025-11-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o3-mini","modelName":"o3-mini","provider":"OpenAI","rawName":"o3-mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":63.89,"unit":"%","rank":142,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-30b-a3b-instruct-jul-2025","modelName":"Qwen3-30B-A3B-Instruct (Jul 2025)","provider":"Alibaba (Qwen)","rawName":"Qwen3-30B-A3B-Instruct (Jul 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":62.22,"unit":"%","rank":144,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-2","modelName":"GPT-5.2","provider":"OpenAI","rawName":"GPT-5.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: none","score":62.22,"unit":"%","rank":144,"rankComputedBySite":true,"date":"2026-07-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-3-mini","modelName":"Grok-3 mini","provider":"xAI","rawName":"Grok-3 mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":62.22,"unit":"%","rank":144,"rankComputedBySite":true,"date":"2025-04-10","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-5-9b","modelName":"Qwen3.5-9B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-9B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":61.67,"unit":"%","rank":147,"rankComputedBySite":true,"date":"2026-08-27","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-5-flash-lite","modelName":"Gemini 3.5 Flash-Lite","provider":"Google","rawName":"Gemini 3.5 Flash-Lite","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":60,"unit":"%","rank":148,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o3","modelName":"o3","provider":"OpenAI","rawName":"o3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":60,"unit":"%","rank":148,"rankComputedBySite":true,"date":"2026-07-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwq-32b","modelName":"QwQ-32B","provider":"Alibaba (Qwen)","rawName":"QwQ-32B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":59.17,"unit":"%","rank":150,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"glm-4-7-flash","modelName":"glm-4.7-flash_none","provider":"Zhipu AI (Z.ai)","rawName":"glm-4.7-flash","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":58.33,"unit":"%","rank":151,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-5","modelName":"GPT-5.5","provider":"OpenAI","rawName":"GPT-5.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: no thinking","score":57.78,"unit":"%","rank":152,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4","modelName":"GPT-5.4","provider":"OpenAI","rawName":"GPT-5.4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: none","score":57.78,"unit":"%","rank":152,"rankComputedBySite":true,"date":"2026-07-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o4-mini","modelName":"o4-mini","provider":"OpenAI","rawName":"o4-mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":57.78,"unit":"%","rank":152,"rankComputedBySite":true,"date":"2026-07-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-7-sonnet","modelName":"Claude 3.7 Sonnet","provider":"Anthropic","rawName":"Claude 3.7 Sonnet","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 64k thinking","score":57.78,"unit":"%","rank":152,"rankComputedBySite":true,"date":"2025-03-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-2-0-flash-thinking-jan-2025","modelName":"Gemini 2.0 Flash Thinking (Jan 2025)","provider":"Google","rawName":"Gemini 2.0 Flash Thinking (Jan 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":57.78,"unit":"%","rank":152,"rankComputedBySite":true,"date":"2025-03-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-5-4b","modelName":"Qwen3.5-4B","provider":"Alibaba (Qwen)","rawName":"Qwen3.5-4B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":55.83,"unit":"%","rank":157,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-r1-distill-qwen-32b","modelName":"DeepSeek-R1-Distill-Qwen-32B","provider":"DeepSeek","rawName":"DeepSeek-R1-Distill-Qwen-32B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":55.56,"unit":"%","rank":158,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-mini","modelName":"GPT-5 mini","provider":"OpenAI","rawName":"GPT-5 mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: minimal","score":55.56,"unit":"%","rank":158,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-3","modelName":"Grok 3","provider":"xAI","rawName":"Grok 3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":55.56,"unit":"%","rank":158,"rankComputedBySite":true,"date":"2025-04-10","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-terra","modelName":"GPT-5.6 Terra","provider":"OpenAI","rawName":"GPT-5.6 Terra","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: none","score":53.33,"unit":"%","rank":161,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o1","modelName":"o1","provider":"OpenAI","rawName":"o1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":53.33,"unit":"%","rank":161,"rankComputedBySite":true,"date":"2026-07-15","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-7-sonnet","modelName":"Claude 3.7 Sonnet","provider":"Anthropic","rawName":"Claude 3.7 Sonnet","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 32k thinking","score":53.33,"unit":"%","rank":161,"rankComputedBySite":true,"date":"2025-03-12","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-r1","modelName":"DeepSeek-R1","provider":"DeepSeek","rawName":"DeepSeek-R1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":53.33,"unit":"%","rank":161,"rankComputedBySite":true,"date":"2025-02-26","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-4b-instruct-2507","modelName":"qwen3-4b-instruct-2507","provider":"Alibaba (Qwen)","rawName":"qwen3-4b-instruct-2507","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":52.22,"unit":"%","rank":165,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-r1-distill-llama-70b","modelName":"DeepSeek-R1-Distill-Llama-70B","provider":"DeepSeek","rawName":"DeepSeek-R1-Distill-Llama-70B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":51.39,"unit":"%","rank":166,"rankComputedBySite":true,"date":"2025-03-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-oss-20b","modelName":"gpt-oss-20b","provider":"OpenAI","rawName":"gpt-oss-20b","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":50.83,"unit":"%","rank":167,"rankComputedBySite":true,"date":"2026-08-27","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-r1-distill-qwen-14b","modelName":"DeepSeek-R1-Distill-Qwen-14B","provider":"DeepSeek","rawName":"DeepSeek-R1-Distill-Qwen-14B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":50.56,"unit":"%","rank":168,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v3-2","modelName":"DeepSeek-V3.2","provider":"DeepSeek","rawName":"DeepSeek-V3.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":48.89,"unit":"%","rank":169,"rankComputedBySite":true,"date":"2026-07-16","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-opus-4-5","modelName":"Claude Opus 4.5","provider":"Anthropic","rawName":"Claude Opus 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: no thinking","score":48.06,"unit":"%","rank":170,"rankComputedBySite":true,"date":"2025-11-24","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o1-mini","modelName":"o1-mini","provider":"OpenAI","rawName":"o1-mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: high","score":46.94,"unit":"%","rank":171,"rankComputedBySite":true,"date":"2025-03-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4-nano","modelName":"GPT-5.4 Nano","provider":"OpenAI","rawName":"GPT-5.4 Nano","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: no thinking","score":46.67,"unit":"%","rank":172,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v4-pro","modelName":"DeepSeek-V4-Pro","provider":"DeepSeek","rawName":"DeepSeek-V4-Pro","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: unknown thinking","score":46.67,"unit":"%","rank":172,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5","modelName":"GPT-5","provider":"OpenAI","rawName":"GPT-5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: minimal","score":46.67,"unit":"%","rank":172,"rankComputedBySite":true,"date":"2026-07-20","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-nano","modelName":"GPT-5 nano","provider":"OpenAI","rawName":"GPT-5 nano","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: low","score":46.67,"unit":"%","rank":172,"rankComputedBySite":true,"date":"2026-07-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-7-sonnet","modelName":"Claude 3.7 Sonnet","provider":"Anthropic","rawName":"Claude 3.7 Sonnet","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: 16k thinking","score":46.67,"unit":"%","rank":172,"rankComputedBySite":true,"date":"2025-02-26","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4-1-mini","modelName":"GPT-4.1 mini","provider":"OpenAI","rawName":"GPT-4.1 mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":44.72,"unit":"%","rank":177,"rankComputedBySite":true,"date":"2025-04-14","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o1-mini","modelName":"o1-mini","provider":"OpenAI","rawName":"o1-mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: medium","score":44.72,"unit":"%","rank":177,"rankComputedBySite":true,"date":"2025-03-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o3-mini","modelName":"o3-mini","provider":"OpenAI","rawName":"o3-mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":44.44,"unit":"%","rank":179,"rankComputedBySite":true,"date":"2026-07-20","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-r1-0528-qwen3-8b","modelName":"deepseek-r1-0528-qwen3-8b","provider":"DeepSeek","rawName":"deepseek-r1-0528-qwen3-8b","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":43.89,"unit":"%","rank":180,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-6-luna","modelName":"GPT-5.6 Luna","provider":"OpenAI","rawName":"GPT-5.6 Luna","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: none","score":40,"unit":"%","rank":181,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4-1","modelName":"GPT-4.1","provider":"OpenAI","rawName":"GPT-4.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":38.33,"unit":"%","rank":182,"rankComputedBySite":true,"date":"2025-04-14","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-1","modelName":"GPT-5.1","provider":"OpenAI","rawName":"GPT-5.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: no thinking","score":37.78,"unit":"%","rank":183,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-3-1-flash-lite","modelName":"Gemini 3.1 Flash-Lite","provider":"Google","rawName":"Gemini 3.1 Flash-Lite","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":37.78,"unit":"%","rank":183,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v3-mar-2025","modelName":"DeepSeek-V3 (Mar 2025)","provider":"DeepSeek","rawName":"DeepSeek-V3 (Mar 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Mar 2025","score":37.78,"unit":"%","rank":183,"rankComputedBySite":true,"date":"2025-04-01","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4-5","modelName":"GPT-4.5","provider":"OpenAI","rawName":"GPT-4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Feb 2025","score":37.78,"unit":"%","rank":183,"rankComputedBySite":true,"date":"2025-02-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-nano","modelName":"GPT-5 nano","provider":"OpenAI","rawName":"GPT-5 nano","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: minimal","score":35.56,"unit":"%","rank":187,"rankComputedBySite":true,"date":"2026-07-13","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-sonnet-4-5","modelName":"Claude Sonnet 4.5","provider":"Anthropic","rawName":"Claude Sonnet 4.5","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: no thinking","score":35.56,"unit":"%","rank":187,"rankComputedBySite":true,"date":"2025-09-29","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-medium-3","modelName":"Mistral Medium 3","provider":"Mistral AI","rawName":"Mistral Medium 3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":32.22,"unit":"%","rank":189,"rankComputedBySite":true,"date":"2025-05-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"o1-preview","modelName":"o1-preview","provider":"OpenAI","rawName":"o1-preview","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":31.11,"unit":"%","rank":190,"rankComputedBySite":true,"date":"2025-03-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-2-0-flash-feb-2025","modelName":"Gemini 2.0 Flash (Feb 2025)","provider":"Google","rawName":"Gemini 2.0 Flash (Feb 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Feb 2025","score":31.11,"unit":"%","rank":190,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-small-3-2","modelName":"Mistral Small 3.2","provider":"Mistral AI","rawName":"Mistral Small 3.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":30.28,"unit":"%","rank":192,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"magistral-small-1-0","modelName":"Magistral Small 1.0","provider":"Mistral AI","rawName":"Magistral Small 1.0","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":30,"unit":"%","rank":193,"rankComputedBySite":true,"date":"2026-08-06","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"glm-5-2","modelName":"GLM-5.2","provider":"Zhipu AI (Z.ai)","rawName":"GLM-5.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":28.89,"unit":"%","rank":194,"rankComputedBySite":true,"date":"2026-08-10","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4-1-nano","modelName":"GPT-4.1 nano","provider":"OpenAI","rawName":"GPT-4.1 nano","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":28.89,"unit":"%","rank":194,"rankComputedBySite":true,"date":"2025-04-14","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"magistral-small-1-2","modelName":"Magistral Small 1.2","provider":"Mistral AI","rawName":"Magistral Small 1.2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":28.06,"unit":"%","rank":196,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"minimax-m3","modelName":"MiniMax-M3","provider":"MiniMax","rawName":"MiniMax-M3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":26.67,"unit":"%","rank":197,"rankComputedBySite":true,"date":"2026-08-10","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-5-4-mini","modelName":"GPT-5.4 Mini","provider":"OpenAI","rawName":"GPT-5.4 Mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: none","score":26.67,"unit":"%","rank":197,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-14b","modelName":"Qwen3-14B","provider":"Alibaba (Qwen)","rawName":"Qwen3-14B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":25.83,"unit":"%","rank":199,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-30b-a3b","modelName":"Qwen3-30B-A3B","provider":"Alibaba (Qwen)","rawName":"Qwen3-30B-A3B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":25.56,"unit":"%","rank":200,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-32b","modelName":"Qwen3-32B","provider":"Alibaba (Qwen)","rawName":"Qwen3-32B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":23.06,"unit":"%","rank":201,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-1-5-pro-sept-2024","modelName":"Gemini 1.5 Pro (Sept 2024)","provider":"Google","rawName":"Gemini 1.5 Pro (Sept 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":23.06,"unit":"%","rank":201,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemma-3-27b","modelName":"Gemma 3 27B","provider":"Google","rawName":"Gemma 3 27B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":22.5,"unit":"%","rank":203,"rankComputedBySite":true,"date":"2026-08-27","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-8b","modelName":"Qwen3-8B","provider":"Alibaba (Qwen)","rawName":"Qwen3-8B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":22.22,"unit":"%","rank":204,"rankComputedBySite":true,"date":"2026-08-27","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-7-sonnet","modelName":"Claude 3.7 Sonnet","provider":"Anthropic","rawName":"Claude 3.7 Sonnet","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":21.94,"unit":"%","rank":205,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-r1-distill-qwen-1-5b","modelName":"DeepSeek-R1-Distill-Qwen-1.5B","provider":"DeepSeek","rawName":"DeepSeek-R1-Distill-Qwen-1.5B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":21.39,"unit":"%","rank":206,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-4-maverick","modelName":"Llama 4 Maverick","provider":"Meta","rawName":"Llama 4 Maverick","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: FP8","score":20.56,"unit":"%","rank":207,"rankComputedBySite":true,"date":"2025-04-08","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen-plus-jan-2025","modelName":"Qwen Plus (Jan 2025)","provider":"Alibaba (Qwen)","rawName":"Qwen Plus (Jan 2025)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":17.78,"unit":"%","rank":208,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemma-3-12b","modelName":"Gemma 3 12B","provider":"Google","rawName":"Gemma 3 12B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":16.67,"unit":"%","rank":209,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-1-5-flash-sep-2024","modelName":"Gemini 1.5 Flash (Sep 2024)","provider":"Google","rawName":"Gemini 1.5 Flash (Sep 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":16.25,"unit":"%","rank":210,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen2-5-max","modelName":"Qwen2.5-Max","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-Max","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":16.11,"unit":"%","rank":211,"rankComputedBySite":true,"date":"2025-04-01","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-v3","modelName":"DeepSeek-V3","provider":"DeepSeek","rawName":"DeepSeek-V3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":15.83,"unit":"%","rank":212,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"phi-4","modelName":"Phi-4","provider":"Microsoft Research","rawName":"Phi-4","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":13.75,"unit":"%","rank":213,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"grok-2-dec-2024","modelName":"Grok-2 (Dec 2024)","provider":"xAI","rawName":"Grok-2 (Dec 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":11.53,"unit":"%","rank":214,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-3-1-405b","modelName":"Llama 3.1-405B","provider":"Meta","rawName":"Llama 3.1-405B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":9.72,"unit":"%","rank":215,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-5-sonnet-october-2024","modelName":"Claude 3.5 Sonnet (October 2024)","provider":"Anthropic","rawName":"Claude 3.5 Sonnet (October 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Oct 2024","score":8.47,"unit":"%","rank":216,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-large-2-jul-2024","modelName":"Mistral Large 2 (Jul 2024)","provider":"Mistral AI","rawName":"Mistral Large 2 (Jul 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":8.47,"unit":"%","rank":216,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen3-1-7b","modelName":"Qwen3-1.7B","provider":"Alibaba (Qwen)","rawName":"Qwen3-1.7B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":8.06,"unit":"%","rank":218,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen2-5-72b","modelName":"Qwen2.5-72B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-72B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":8.06,"unit":"%","rank":218,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-4-scout","modelName":"Llama 4 Scout","provider":"Meta","rawName":"Llama 4 Scout","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":7.78,"unit":"%","rank":220,"rankComputedBySite":true,"date":"2025-04-08","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-large-2-nov-2024","modelName":"Mistral Large 2 (Nov 2024)","provider":"Mistral AI","rawName":"Mistral Large 2 (Nov 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":7.78,"unit":"%","rank":220,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemma-3-4b","modelName":"Gemma 3 4B","provider":"Google","rawName":"Gemma 3 4B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":7.5,"unit":"%","rank":222,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen2-5-32b","modelName":"Qwen2.5-32B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-32B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":7.36,"unit":"%","rank":223,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4o-mini","modelName":"GPT-4o mini","provider":"OpenAI","rawName":"GPT-4o mini","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":6.94,"unit":"%","rank":224,"rankComputedBySite":true,"date":"2025-07-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-1-5-pro-may-2024","modelName":"Gemini 1.5 Pro (May 2024)","provider":"Google","rawName":"Gemini 1.5 Pro (May 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":6.81,"unit":"%","rank":225,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-small-3","modelName":"Mistral Small 3","provider":"Mistral AI","rawName":"Mistral Small 3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":6.67,"unit":"%","rank":226,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4-turbo-apr-2024","modelName":"GPT-4 Turbo (Apr 2024)","provider":"OpenAI","rawName":"GPT-4 Turbo (Apr 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":6.67,"unit":"%","rank":226,"rankComputedBySite":true,"date":"2025-02-27","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-5-sonnet","modelName":"Claude 3.5 Sonnet","provider":"Anthropic","rawName":"Claude 3.5 Sonnet","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Jun 2024","score":6.53,"unit":"%","rank":228,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4o-aug-2024","modelName":"GPT-4o (Aug 2024)","provider":"OpenAI","rawName":"GPT-4o (Aug 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Aug 2024","score":6.39,"unit":"%","rank":229,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4o-may-2024","modelName":"GPT-4o (May 2024)","provider":"OpenAI","rawName":"GPT-4o (May 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: May 2024","score":6.25,"unit":"%","rank":230,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4o-nov-2024","modelName":"GPT-4o (Nov 2024)","provider":"OpenAI","rawName":"GPT-4o (Nov 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Nov 2024","score":6.25,"unit":"%","rank":230,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen-turbo","modelName":"Qwen-Turbo","provider":"Alibaba (Qwen)","rawName":"Qwen-Turbo","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":6.11,"unit":"%","rank":232,"rankComputedBySite":true,"date":"2025-04-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-3-3-70b","modelName":"Llama 3.3 70B","provider":"Meta","rawName":"Llama 3.3 70B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":5.14,"unit":"%","rank":233,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-opus","modelName":"Claude 3 Opus","provider":"Anthropic","rawName":"Claude 3 Opus","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":4.72,"unit":"%","rank":234,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-1-5-flash-8b","modelName":"Gemini 1.5 Flash 8B","provider":"Google","rawName":"Gemini 1.5 Flash 8B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":4.58,"unit":"%","rank":235,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"tulu-3-t-lu-3-70b","modelName":"Tulu 3 (Tülu 3) 70B","provider":"Ai2","rawName":"Tulu 3 (Tülu 3) 70B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":4.44,"unit":"%","rank":236,"rankComputedBySite":true,"date":"2025-03-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-3-70b","modelName":"Llama 3-70B","provider":"Meta","rawName":"Llama 3-70B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":4.31,"unit":"%","rank":237,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-5-haiku","modelName":"Claude 3.5 Haiku","provider":"Anthropic","rawName":"Claude 3.5 Haiku","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Oct 2024","score":4.31,"unit":"%","rank":237,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-small-3-1","modelName":"Mistral Small 3.1","provider":"Mistral AI","rawName":"Mistral Small 3.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":3.89,"unit":"%","rank":239,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-1-5-flash-may-2024","modelName":"Gemini 1.5 Flash (May 2024)","provider":"Google","rawName":"Gemini 1.5 Flash (May 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: May 2024","score":3.89,"unit":"%","rank":239,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-3-1-70b","modelName":"Llama 3.1-70B","provider":"Meta","rawName":"Llama 3.1-70B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":3.61,"unit":"%","rank":241,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"granite-4-0-micro","modelName":"granite-4.0-micro","provider":"IBM","rawName":"granite-4.0-micro","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":2.78,"unit":"%","rank":242,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-3-2-90b","modelName":"Llama 3.2 90B","provider":"Meta","rawName":"Llama 3.2 90B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":2.64,"unit":"%","rank":243,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"qwen2-5-7b","modelName":"Qwen2.5-7B","provider":"Alibaba (Qwen)","rawName":"Qwen2.5-7B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":2.5,"unit":"%","rank":244,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"hermes-2-theta-llama-3-70b","modelName":"Hermes 2 Theta Llama-3 70B","provider":"Nous Research","rawName":"Hermes 2 Theta Llama-3 70B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":2.5,"unit":"%","rank":244,"rankComputedBySite":true,"date":"2025-04-01","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-2","modelName":"Claude 2","provider":"Anthropic","rawName":"Claude 2","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":2.5,"unit":"%","rank":244,"rankComputedBySite":true,"date":"2025-03-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-sonnet","modelName":"Claude 3 Sonnet","provider":"Anthropic","rawName":"Claude 3 Sonnet","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":2.5,"unit":"%","rank":244,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-3-5-turbo-jan-2024","modelName":"GPT-3.5 Turbo (Jan 2024)","provider":"OpenAI","rawName":"GPT-3.5 Turbo (Jan 2024)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Jan 2024","score":2.22,"unit":"%","rank":248,"rankComputedBySite":true,"date":"2026-08-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-3-8b","modelName":"Llama 3-8B","provider":"Meta","rawName":"Llama 3-8B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":1.94,"unit":"%","rank":249,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-2-1","modelName":"Claude 2.1","provider":"Anthropic","rawName":"Claude 2.1","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":1.94,"unit":"%","rank":249,"rankComputedBySite":true,"date":"2025-03-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-large","modelName":"Mistral Large","provider":"Mistral AI","rawName":"Mistral Large","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":1.94,"unit":"%","rank":249,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"claude-3-haiku","modelName":"Claude 3 Haiku","provider":"Anthropic","rawName":"Claude 3 Haiku","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":1.81,"unit":"%","rank":252,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-3-1-8b","modelName":"Llama 3.1-8B","provider":"Meta","rawName":"Llama 3.1-8B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":1.67,"unit":"%","rank":253,"rankComputedBySite":true,"date":"2026-08-27","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemma-2-27b","modelName":"Gemma 2 27B","provider":"Google","rawName":"Gemma 2 27B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":1.39,"unit":"%","rank":254,"rankComputedBySite":true,"date":"2025-03-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemma-3-1b","modelName":"Gemma 3 1B","provider":"Google","rawName":"Gemma 3 1B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":1.11,"unit":"%","rank":255,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4-jun-2023","modelName":"GPT-4 (Jun 2023)","provider":"OpenAI","rawName":"GPT-4 (Jun 2023)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Jun 2023","score":1.11,"unit":"%","rank":255,"rankComputedBySite":true,"date":"2025-10-23","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemini-1-0-pro","modelName":"Gemini 1.0 Pro","provider":"Google","rawName":"Gemini 1.0 Pro","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":1.11,"unit":"%","rank":255,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"granite-4-0-1b","modelName":"granite-4.0-1b","provider":"IBM","rawName":"granite-4.0-1b","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":0.83,"unit":"%","rank":258,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"deepseek-llm-67b","modelName":"DeepSeek LLM 67B","provider":"DeepSeek","rawName":"DeepSeek LLM 67B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":0.83,"unit":"%","rank":258,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-3-2-1b","modelName":"Llama 3.2 1B","provider":"Meta","rawName":"Llama 3.2 1B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":0.56,"unit":"%","rank":260,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gpt-4-mar-2023","modelName":"GPT-4 (Mar 2023)","provider":"OpenAI","rawName":"GPT-4 (Mar 2023)","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025; effort: Mar 2023","score":0.56,"unit":"%","rank":260,"rankComputedBySite":true,"date":"2025-10-22","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"gemma-2-9b","modelName":"Gemma 2 9B","provider":"Google","rawName":"Gemma 2 9B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":0.56,"unit":"%","rank":260,"rankComputedBySite":true,"date":"2025-03-07","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"mistral-7b-v0-3","modelName":"Mistral 7B v0.3","provider":"Mistral AI","rawName":"Mistral 7B v0.3","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":0.28,"unit":"%","rank":263,"rankComputedBySite":true,"date":"2026-08-30","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"granite-4-0-350m","modelName":"granite-4.0-350m","provider":"IBM","rawName":"granite-4.0-350m","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":0.28,"unit":"%","rank":263,"rankComputedBySite":true,"date":"2026-08-28","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"},{"model":"llama-2-70b","modelName":"Llama 2-70B","provider":"Meta","rawName":"Llama 2-70B","variant":"epoch","setting":"Epoch AI run, OTIS Mock AIME 2024–2025","score":0,"unit":"%","rank":265,"rankComputedBySite":true,"date":"2025-02-25","sourceType":"independent","source":"epoch","sourceUrl":"https://epoch.ai/benchmarks","collected":"2026-10-10"}]}