← Artificial Analysis leaderboards
Humanity's Last Exam
Artificial Analysis · 50 models
| Rank | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (Max, Default Fallback) | 0.614 |
| 2 | Claude Fable 5.1 (Max, Default Fallback) | 0.591 |
| 3 | Claude Fable 5.1 (Xhigh, Default Fallback) | 0.587 |
| 4 | Claude Opus 5.5 (Xhigh, Default Fallback) | 0.575 |
| 5 | Gemini 4 Argon (High) | 0.571 |
| 6 | Claude Fable 5.1 (High, Default Fallback) | 0.559 |
| 7 | Claude Opus 5.5 (High, Default Fallback) | 0.556 |
| 8 | Claude Fable 5 (Max, Opus 4.8 Fallback) | 0.555 |
| 9 | Claude Sonnet 5.5 (Max, Default Fallback) | 0.55 |
| 10 | Claude Opus 5 (Max) | 0.549 |
| 11 | Claude Opus 5.5 (Medium, Default Fallback) | 0.547 |
| 11 | GPT-6 Astra (Max) | 0.547 |
| 13 | GPT-6 Astra (Xhigh) | 0.546 |
| 14 | Claude Opus 5 (Xhigh) | 0.544 |
| 15 | Claude Fable 5.1 (Medium, Default Fallback) | 0.538 |
| 16 | Muse Wonder Full (Max) | 0.536 |
| 17 | GPT-6 Astra (High) | 0.531 |
| 18 | GPT-6.1 Sol (Max) | 0.529 |
| 19 | Claude Opus 5 (High) | 0.528 |
| 20 | GPT-6 Astra (Medium) | 0.527 |
| 21 | GPT-6.1 Sol (Xhigh) | 0.526 |
| 22 | Kimi K3.1 Pro | 0.525 |
| 23 | GPT-6.1 Sol (High) | 0.514 |
| 24 | Claude Opus 5 (Medium) | 0.513 |
| 25 | Muse Wonder (Max) | 0.501 |
| 26 | Claude Sonnet 5.5 (Xhigh, Default Fallback) | 0.5 |
| 27 | GPT-6.1 Sol (Medium) | 0.499 |
| 28 | GPT-5.6 Sol (Max) | 0.495 |
| 29 | MiMo-V2.6-Pro | 0.494 |
| 30 | GPT-6 Astra (Low) | 0.492 |
| 31 | Claude Fable 5.1 (Low, Default Fallback) | 0.489 |
| 32 | Claude Opus 4.8 (Max) | 0.487 |
| 32 | Muse Spark 1.3 (Max) | 0.487 |
| 34 | Claude Opus 5.5 (Low, Default Fallback) | 0.483 |
| 35 | MiniMax-M3.1-Flash | 0.48 |
| 36 | GPT-6 Sol (Max) | 0.479 |
| 36 | Gemini 3.7 Flash (High) | 0.479 |
| 38 | Gemini 3.8 Flash (High) | 0.478 |
| 39 | Muse Spark 1.3 (Xhigh) | 0.475 |
| 40 | GPT-6.1 Sol (Low) | 0.474 |
| 41 | GPT-5.6 Sol (Xhigh) | 0.473 |
| 42 | Gemini 3.1 Pro Preview | 0.47 |
| 43 | Kimi K3 (Max) | 0.469 |
| 44 | Step 5 Preview | 0.465 |
| 45 | GPT-6 Sol (Xhigh) | 0.463 |
| 46 | GPT-6.1 Terra (Max) | 0.462 |
| 46 | Muse Spark 1.1 (Xhigh) | 0.462 |
| 48 | GPT-5.6 Sol (High) | 0.46 |
| 49 | Claude Sonnet 5.5 (High, Default Fallback) | 0.458 |
| 49 | GPT-5.5 (Xhigh) | 0.458 |