OTIS Mock AIME 2024-2025
Each model’s result as Epoch AI’s Benchmarking Hub publishes it, run by Epoch or collected from the source it cites. Facthory has not run them.
Data: Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks, licensed CC BY 4.0. Read on 16 Nov 2026.
The chart shows the 25 best and the table the 100 best of 316 results.
| # | Model | Organization | Result | Evidence |
|---|---|---|---|---|
| 1 | Claude Fable 5.1 (max) API access | Anthropic | 100% ± 0% | Log or source |
| 2 | Claude Fable 5 (high) API access | Anthropic | 100% ± 0% | Log or source |
| 3 | Claude Opus 5.5 (max) API access | Anthropic | 100% ± 0% | Log or source |
| 4 | Claude Sonnet 5.5 (max) API access | Anthropic | 100% ± 0% | Log or source |
| 5 | Gemini 4 Argon (high) API access | Google DeepMind | 100% ± 0% | Log or source |
| 6 | Gemini 4 Carbon (high) API access | Google DeepMind | 100% ± 0% | – |
| 7 | GPT-5.5 (xhigh) API access | OpenAI | 100% ± 0% | Log or source |
| 8 | GPT-5.5 Pro (xhigh) API access | OpenAI | 100% ± 0% | Log or source |
| 9 | GPT-5.6 Sol (max) API access | OpenAI | 100% ± 0% | Log or source |
| 10 | GPT-6 Astra (max) API access | OpenAI | 100% ± 0% | Log or source |
| 11 | GPT-6 Sol (max) API access | OpenAI | 100% ± 0% | Log or source |
| 12 | GPT-6.1 Sol (max) API access | OpenAI | 100% ± 0% | Log or source |
| 13 | GPT-6.1 Terra (max) API access | OpenAI | 100% ± 0% | Log or source |
| 14 | Kimi K3.1 Pro (Together, max) Open weights (restricted use) | Moonshot | 100% ± 0% | Log or source |
| 15 | Qwen3.8 Max (0902) (xhigh) API access | Alibaba | 100% ± 0% | Log or source |
| 16 | Claude Fable 5.2 (max) API access | Anthropic | 99.7% ± 0.3% | – |
| 17 | Claude Fable 5 (max) API access | Anthropic | 99.7% ± 0.3% | Log or source |
| 18 | GPT-5.6 Terra (max) API access | OpenAI | 99.7% ± 0.3% | Log or source |
| 19 | DeepSeek V4.1 Flash 1017 (max) Open weights (unrestricted) | DeepSeek | 99.4% ± 0.4% | Log or source |
| 20 | Mistral Large 4 (high) Open weights (restricted use) | Mistral AI | 99.4% ± 0.4% | Log or source |
| 21 | Muse Wonder (max) API access | Meta AI | 99.4% ± 0.4% | Log or source |
| 22 | Qwen3.8 Max (xhigh) API access | Alibaba | 99.4% ± 0.4% | Log or source |
| 23 | Doubao Seed Evolving (Nov 2026, high) API access | ByteDance | 99.2% ± 0.5% | Log or source |
| 24 | Grok 4.6 (xhigh) API access | xAI | 99.2% ± 0.5% | Log or source |
| 25 | Muse Spark 1.3 (xhigh) API access | Meta AI | 99.2% ± 0.6% | Log or source |
| 26 | Claude Haiku 5.5 (xhigh) API access | Anthropic | 98.9% ± 0.5% | Log or source |
| 27 | Claude Opus 5 (max) API access | Anthropic | 98.9% ± 1.1% | Log or source |
| 28 | Gemini 3.8 Flash (high) API access | Google DeepMind | 98.9% ± 0.9% | Log or source |
| 29 | GPT-6 Luna (max) API access | OpenAI | 98.9% ± 0.7% | Log or source |
| 30 | DeepSeek V4 Pro 0813 (max) Open weights (unrestricted) | DeepSeek | 98.6% ± 1% | Log or source |
| 31 | Claude Opus 4.8 API access | Anthropic | 98.3% ± 1.4% | Log or source |
| 32 | DeepSeek V4.1 Flash (max) Open weights (unrestricted) | DeepSeek | 98.3% ± 0.6% | Log or source |
| 33 | GPT-5.6 Luna (max) API access | OpenAI | 98.3% ± 1.2% | Log or source |
| 34 | Mistral Large 4 Preview (high) Open weights (restricted use) | Mistral AI | 98.3% ± 0.6% | Log or source |
| 35 | Muse Spark Open (xhigh) Open weights (restricted use) | Meta AI | 98.1% ± 1.3% | Log or source |
| 36 | Grok 4.7 (xhigh) API access | xAI | 98.1% ± 1.4% | Log or source |
| 37 | Claude Opus 4.7 (xhigh) API access | Anthropic | 97.8% ± 2.2% | Log or source |
| 38 | Claude Fable 5 (low) API access | Anthropic | 97.8% ± 2.2% | Log or source |
| 39 | Claude Opus 4.8 API access | Anthropic | 97.8% ± 2.2% | Log or source |
| 40 | Claude Opus 5 API access | Anthropic | 97.8% ± 2.2% | Log or source |
| 41 | GPT-5.4 (high) API access | OpenAI | 97.8% ± 2.2% | Log or source |
| 42 | Grok 4.5 (high) API access | xAI | 97.8% ± 1.3% | Log or source |
| 43 | Grok 4.6 (high) API access | xAI | 97.8% ± 1% | Log or source |
| 44 | Claude Haiku 5.5 (high) API access | Anthropic | 97.2% ± 1.3% | Log or source |
| 45 | Gemini 3.7 Flash (high) API access | Google DeepMind | 97.2% ± 1.9% | Log or source |
| 46 | Kimi K3 (max) Open weights (non-commercial) | Moonshot | 97.2% ± 1.1% | Log or source |
| 47 | DeepSeek v4 Pro (max) Open weights (unrestricted) | DeepSeek | 96.7% ± 2% | Log or source |
| 48 | Doubao Seed 2.1 Turbo (high) API access | ByteDance | 96.1% ± 2.5% | Log or source |
| 49 | GPT-5.2 (high) API access | OpenAI | 96.1% ± 2.6% | Log or source |
| 50 | Kimi K2.6 Open weights (unrestricted) | Moonshot | 96.1% ± 2.4% | Log or source |
| 51 | GPT-5.2 (xhigh) API access | OpenAI | 96.1% ± 2.7% | Log or source |
| 52 | Gemini 3.1 Pro Preview API access | Google DeepMind | 95.6% ± 3.1% | Log or source |
| 53 | DeepSeek v4 Pro (high) Open weights (unrestricted) | DeepSeek | 95.6% ± 3.1% | Log or source |
| 54 | Doubao Seed 2.1 Pro (high) API access | ByteDance | 95.6% ± 2.9% | Log or source |
| 55 | Gemini 3 Flash Preview API access | Google DeepMind | 95.6% ± 3.1% | Log or source |
| 56 | Gemini 3.1 Pro Preview API access | Google DeepMind | 95.6% ± 3.1% | Log or source |
| 57 | Gemini 3.5 Flash API access | Google DeepMind | 95.6% ± 2.7% | Log or source |
| 58 | GPT-5.4 (medium) API access | OpenAI | 95.6% ± 3.1% | Log or source |
| 59 | GPT-5.6 Sol (low) API access | OpenAI | 95.6% ± 3.1% | Log or source |
| 60 | Kimi K2.7 Code Open weights (unrestricted) | Moonshot | 95.6% ± 3.1% | Log or source |
| 61 | Qwen3.7 Max API access | Alibaba | 95.6% ± 3.1% | Log or source |
| 62 | GPT-5.4 (xhigh) API access | OpenAI | 95.3% ± 3.2% | Log or source |
| 63 | Claude Sonnet 5 (xhigh) API access | Anthropic | 94.7% ± 2.3% | Log or source |
| 64 | Claude Opus 4.6 (64k thinking) API access | Anthropic | 94.4% ± 2.8% | Log or source |
| 65 | DeepSeek V4 Flash 0731 (max) Open weights (unrestricted) | DeepSeek | 94.4% ± 2.1% | Log or source |
| 66 | Gemini 3.6 Flash API access | Google DeepMind | 94.2% ± 3.1% | Log or source |
| 67 | Doubao-Seed-2.0 Pro (high) API access | ByteDance | 93.9% ± 2.7% | Log or source |
| 68 | GLM-5.3-Flash (max) Open weights (unrestricted) | Z.ai (Zhipu AI) | 93.9% ± 2.2% | Log or source |
| 69 | GPT-5.2 (medium) API access | OpenAI | 93.9% ± 3.1% | Log or source |
| 70 | Claude Opus 5 (low) API access | Anthropic | 93.3% ± 3.8% | Log or source |
| 71 | GLM-5.1 Open weights (unrestricted) | Z.ai (Zhipu AI) | 93.3% ± 3.8% | Log or source |
| 72 | grok-4.3_high Hosted access (no API) | xAI | 93.3% ± 3% | Log or source |
| 73 | Kimi K3 (high) Open weights (non-commercial) | Moonshot | 93.3% ± 3.8% | Log or source |
| 74 | Qwen 3.6 Plus (2026-04-02) API access | Alibaba | 93.3% ± 3.8% | Log or source |
| 75 | Qwen3.7 Plus API access | Alibaba | 93.3% ± 3.8% | Log or source |
| 76 | Claude Opus 4.6 (32k thinking) API access | Anthropic | 93.1% ± 3.3% | Log or source |
| 77 | Gemini 3 Flash Preview API access | Google DeepMind | 92.8% ± 3.5% | Log or source |
| 78 | grok-4.20-0309-reasoning API access | xAI | 92.2% ± 3.3% | Log or source |
| 79 | Kimi K2.5 (Fireworks) Open weights (unrestricted) | Moonshot | 92.2% ± 3.9% | Log or source |
| 80 | Gemini 3 Pro Preview API access | Google DeepMind | 91.4% ± 3.7% | Log or source |
| 81 | GPT-5 (high) API access | OpenAI | 91.4% ± 3.7% | Log or source |
| 82 | Claude Opus 4.6 (max) API access | Anthropic | 91.1% ± 4.3% | Log or source |
| 83 | Doubao Seed 2.0 Lite (Apr 2026, high) API access | ByteDance | 91.1% ± 3.6% | Log or source |
| 84 | GLM-5.3 (max) Open weights (restricted use) | Z.ai (Zhipu AI) | 91.1% ± 3.5% | Log or source |
| 85 | Qwen3.6 27B Open weights (unrestricted) | Alibaba | 91.1% ± 4.3% | Log or source |
| 86 | Qwen 3.6 Max (Preview) | Alibaba | 91.1% ± 4.3% | Log or source |
| 87 | Inkling Small (xhigh) Open weights (unrestricted) | Thinking Machines | 90% ± 4% | Log or source |
| 88 | Muse Spark API access | Meta AI | 88.9% ± 4.7% | – |
| 89 | Inkling (xhigh) Open weights (unrestricted) | Thinking Machines | 88.9% ± 3.9% | Log or source |
| 90 | Gemini 3.5 Flash API access | Google DeepMind | 88.9% ± 4.7% | Log or source |
| 91 | GPT-5.4 mini (xhigh) API access | OpenAI | 88.9% ± 4.7% | Log or source |
| 92 | GPT-5.6 Terra (low) API access | OpenAI | 88.9% ± 4.7% | Log or source |
| 93 | openai/gpt-oss-120b_high Open weights (unrestricted) | OpenAI | 88.9% ± 4.5% | Log or source |
| 94 | Qwen3.5 397B-A17B Open weights (unrestricted) | Alibaba | 88.9% ± 4.7% | Log or source |
| 95 | GPT-5.1 (high) API access | OpenAI | 88.6% ± 4% | Log or source |
| 96 | DeepSeek-V3.2 (Thinking) Open weights (unrestricted) | DeepSeek | 87.8% ± 4.1% | Log or source |
| 97 | GPT-5.4 nano (high) API access | OpenAI | 87.8% ± 3.9% | Log or source |
| 98 | GPT-5 (medium) API access | OpenAI | 87.2% ± 3.9% | Log or source |
| 99 | GPT-5.4 mini (high) API access | OpenAI | 87.2% ± 4.3% | Log or source |
| 100 | Qwen3-235B-A22B-Thinking-2507 Open weights (unrestricted) | Alibaba | 86.7% ± 5.1% | Log or source |
