| # | Model | Score | Relative | Setting | Released | Run | Evidence |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 Anthropic | 100.0% | max | 1 Sep 2026 | — | Source ↗ | |
| 2 | GPT-6 Astra (unknown thinking) OpenAI | 99.0% | unknown | 3 Sep 2026 | — | Source ↗ | |
| 3 | Claude Opus 5 Anthropic | 99.0% | max | 24 Jul 2026 | — | Source ↗ | |
| 4 | Claude Fable 5 Anthropic | 95.0% | max | 9 Jun 2026 | — | Source ↗ | |
| 5 | Kimi K3 (unknown) Open source Moonshot | 87.0% | unknown | 16 Jul 2026 | — | Source ↗ | |
| 6 | GPT-5.6 Sol OpenAI | 83.0% | max | 9 Jul 2026 | — | Source ↗ | |
| 7 | Claude Sonnet 5 Anthropic | 77.0% | max | 30 Jun 2026 | — | Source ↗ | |
| 8 | Tencent Hy4 preview (unknown) Open source Tencent | 75.0% | unknown | 28 Aug 2026 | — | Source ↗ | |
| 9 | GPT-5.6 Terra (xhigh) OpenAI | 74.0% | xhigh | 9 Jul 2026 | — | Source ↗ | |
| 10 | Claude Opus 4.8 Anthropic | 69.0% | max | 28 May 2026 | — | Source ↗ | |
| 11 | GPT-5.6 Luna OpenAI | 60.0% | max | 9 Jul 2026 | — | Source ↗ | |
| 12 | Gemini 3.7 Flash (unknown) Google DeepMind | 58.0% | unknown | 13 Aug 2026 | — | Source ↗ | |
| 13 | Qwen3.8 Max (unknown) Alibaba | 58.0% | unknown | 2 Aug 2026 | — | Source ↗ | |
| 14 | DeepSeek V4 Flash 0731 (unknown) Open source DeepSeek | 56.0% | unknown | 31 Jul 2026 | — | Source ↗ | |
| 15 | GPT-5.4 (xhigh) OpenAI | 56.0% | xhigh | 5 Mar 2026 | — | Source ↗ | |
| 16 | DeepSeek V4.1 Flash (unknown) Open source DeepSeek | 54.0% | unknown | 9 Sep 2026 | — | Source ↗ | |
| 17 | Claude Opus 4.7 Anthropic | 54.0% | max | 16 Apr 2026 | — | Source ↗ | |
| 18 | Grok 4.6 (unknown) xAI | 51.0% | unknown | 12 Aug 2026 | — | Source ↗ | |
| 19 | DeepSeek V4 Pro 0813 (unknown) Open source DeepSeek | 50.0% | unknown | 13 Aug 2026 | — | Source ↗ | |
| 20 | GPT-5.5 (xhigh) OpenAI | 50.0% | xhigh | 23 Apr 2026 | — | Source ↗ | |
| 21 | Claude Opus 4.6 Anthropic | 50.0% | max | 5 Feb 2026 | — | Source ↗ | |
| 22 | GLM 5.3 Open source Z.ai | 49.0% | max | 14 Aug 2026 | — | Source ↗ | |
| 23 | Gemini 3.8 Flash (unknown) Google DeepMind | 48.0% | unknown | 2 Sep 2026 | — | Source ↗ | |
| 24 | Claude Sonnet 4.6 Anthropic | 45.0% | max | 17 Feb 2026 | — | Source ↗ | |
| 25 | Muse Spark 1.2 Meta | 43.0% | — | 5 Aug 2026 | — | Source ↗ | |
| 26 | Muse Spark 1.1 Meta | 39.0% | — | 9 Jul 2026 | — | Source ↗ | |
| 27 | Gemini 3.6 Flash Google | 36.0% | unknown | 21 Jul 2026 | — | Source ↗ | |
| 28 | Claude Opus 4.5 (unknown thinking) Anthropic | 36.0% | unknown | 24 Nov 2025 | — | Source ↗ | |
| 29 | GLM 5.2 Open source Z.ai | 35.0% | max | 16 Jun 2026 | — | Source ↗ | |
| 30 | Grok 4.7 (unknown) xAI | 34.0% | unknown | 21 Sep 2026 | — | Source ↗ | |
| 31 | Grok 4.5 SpaceXAI | 31.0% | high | 8 Jul 2026 | — | Source ↗ | |
| 32 | Gemini 3.5 Flash Google | 31.0% | high | 19 May 2026 | — | Source ↗ | |
| 33 | Qwen3.7 Max Qwen | 26.0% | — | 19 May 2026 | — | Source ↗ | |
| 34 | Gemini 3.1 Pro Preview Google | 26.0% | — | 19 Feb 2026 | — | Source ↗ | |
| 35 | GLM 5.1 Open source Z.ai | 22.2% | — | 7 Apr 2026 | — | Source ↗ | |
| 36 | MiMo-V2.5-Pro Open source Xiaomi | 22.0% | — | 22 Apr 2026 | — | Source ↗ | |
| 37 | GLM 5.3 Flash Open source Z.ai | 21.0% | max | 20 Aug 2026 | — | Source ↗ | |
| 38 | GPT-5.4 mini (xhigh) OpenAI | 21.0% | xhigh | 17 Mar 2026 | — | Source ↗ | |
| 39 | Gemini 3 Pro Preview Google DeepMind | 20.0% | — | 18 Nov 2025 | — | Source ↗ | |
| 40 | Claude Sonnet 4.5 (unknown thinking) Anthropic | 19.0% | unknown | 29 Sep 2025 | — | Source ↗ | |
| 41 | MiniMax M3 Open source MiniMax | 18.0% | — | 1 Jun 2026 | — | Source ↗ | |
| 42 | GPT-5 OpenAI | 18.0% | high | 7 Aug 2025 | — | Source ↗ | |
| 43 | Muse Spark Meta AI | 17.0% | — | 8 Apr 2026 | — | Source ↗ | |
| 44 | Qwen3.8 27B Open source Qwen | 16.0% | — | 14 Aug 2026 | — | Source ↗ | |
| 45 | DeepSeek v4 Pro (high) Open source DeepSeek | 16.0% | max | 24 Apr 2026 | — | Source ↗ | |
| 46 | MiMo-V2.5 Open source Xiaomi | 16.0% | — | 22 Apr 2026 | — | Source ↗ | |
| 47 | Kimi K2.6 Open source MoonshotAI | 16.0% | — | 20 Apr 2026 | — | Source ↗ | |
| 48 | Gemini 3 Flash Preview Google | 15.0% | — | 17 Dec 2025 | — | Source ↗ | |
| 49 | GPT-5.2 (xhigh) OpenAI | 15.0% | xhigh | 11 Dec 2025 | — | Source ↗ | |
| 50 | Grok 4.20 SpaceXAI | 14.0% | — | 17 Feb 2026 | — | Source ↗ | |
| 51 | Gemini 3.5 Flash Lite Google | 13.0% | — | 21 Jul 2026 | — | Source ↗ | |
| 52 | GPT-5 Nano OpenAI | 12.0% | high | 7 Aug 2025 | — | Source ↗ | |
| 53 | Grok 4.3 Beta xAI | 11.0% | high | 17 Apr 2026 | — | Source ↗ | |
| 54 | Mistral Medium 3.5 Open source Mistral | 9.0% | — | 28 Apr 2026 | — | Source ↗ | |
| 55 | GPT-5.1-Codex-Max OpenAI | 9.0% | — | 4 Dec 2025 | — | Source ↗ | |
| 56 | GPT-5 Mini OpenAI | 9.0% | high | 7 Aug 2025 | — | Source ↗ | |
| 57 | DeepSeek-V3.2 (Thinking; Fireworks) Open source DeepSeek | 8.0% | — | 1 Dec 2025 | — | Source ↗ | |
| 58 | Inkling Small Open source Thinking Machines | 6.0% | — | 15 Jul 2026 | — | Source ↗ | |
| 59 | GLM 4.7 Open source Z.ai | 6.0% | — | 22 Dec 2025 | — | Source ↗ | |
| 60 | GPT-5.4 Nano OpenAI | 5.0% | high | 17 Mar 2026 | — | Source ↗ | |
| 61 | MiniMax M2.5 Open source MiniMax | 4.0% | — | 12 Feb 2026 | — | Source ↗ | |
| 62 | Grok 4.1 Fast xAI | 4.0% | — | 19 Nov 2025 | — | Source ↗ | |
| 63 | Mercury 2.5 (unknown) Inception Labs | 3.0% | unknown | 8 Sep 2026 | — | Source ↗ | |
| 64 | MiniMax M2.7 Open source MiniMax | 3.0% | — | 18 Mar 2026 | — | Source ↗ | |
| 65 | Nemotron 3 Ultra Open source NVIDIA | 2.0% | — | 4 Jun 2026 | — | Source ↗ | |
| 66 | Inkling Open source Thinking Machines | 0.0% | — | 15 Jul 2026 | — | Source ↗ | |
| 67 | Laguna M.1 Poolside | 0.0% | — | 28 Apr 2026 | — | Source ↗ | |
| 68 | Laguna XS.2 Open source Poolside | 0.0% | — | 28 Apr 2026 | — | Source ↗ |
Caveats: settings (reasoning effort, agent scaffold) differ between rows and materially affect scores; the best reported setting per model is shown. Source: Epoch AI, CC BY 4.0.