Humanity's Last Exam
Rank #3 of 51 · 37 models scored · top score 43.74
Frontier expert knowledge/reasoning across 100+ subjects
Strongest on discrimination, weakest on saturation headroom. Caveat: the public test set leaves contamination on the table.
Weighted composite. Each signal is computed from the source-backed leaderboard below.
Does it still separate models?
How far from ceiling / clustered at the top?
Public vs held-out; training-leak risk.
Apples-to-apples, or mixed / vendor-optimized?
How old is the benchmark?
| # | Model | Score | Evidence | Measured |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro | 43.74 | unverified | 2026-02-19 |
| 2 | GPT-5.4 Pro | 41.51 | unverified | 2026-03-05 |
| 3 | Muse Spark | 37.56 | unverified | 2026-04-08 |
| 4 | Gemini 3 Pro | 34.37 | unverified | 2025-11-18 |
| 5 | GPT-5.4 | 33.03 | unverified | 2026-03-05 |
| 6 | Claude Opus 4.7 | 32.98 | unverified | 2026-04-16 |
| 7 | Claude Opus 4.6 | 31.13 | unverified | 2026-02-05 |
| 8 | GPT-5 Pro | 28.19 | unverified | 2025-10-07 |
| 9 | GPT-5.2 | 24.16 | unverified | 2025-12-11 |
| 10 | GPT-5 | 21.55 | unverified | 2025-08-07 |
| 11 | Claude Opus 4.5 | 21.43 | unverified | 2025-11-24 |
| 12 | Kimi K2.5 | 20.56 | unverified | 2026-02-02 |
| 13 | GPT-5.1 | 19.83 | unverified | 2025-11-13 |
| 14 | Gemini 2.5 Pro (Jun 2025) | 17.69 | unverified | 2025-06-05 |
| 15 | o3 | 16.3 | unverified | 2024-12-20 |
| 16 | GPT-5 mini | 15.38 | unverified | 2025-08-07 |
| 17 | Gemini 2.5 Pro (Mar 2025) | 14.03 | unverified | 2025-03-25 |
| 18 | o4-mini | 13.95 | unverified | 2025-04-16 |
| 19 | Gemini 2.5 Pro (May 2025) | 13.66 | unverified | 2025-05-06 |
| 20 | Claude Sonnet 4.5 | 9.37 | unverified | 2025-09-29 |
| 21 | Gemini 2.5 Flash (Apr 2025) | 7.65 | unverified | 2025-04-17 |
| 22 | Claude Opus 4.1 | 7.06 | unverified | 2025-08-05 |
| 23 | Gemini 2.5 Flash (May 2025) | 6.47 | unverified | 2025-05-20 |
| 24 | Claude Opus 4 | 6.22 | unverified | 2025-05-22 |
| 25 | Gemini 3.1 Flash-Lite | 4.03 | unverified | 2026-03-03 |
| 26 | Claude 3.7 Sonnet | 3.4 | unverified | 2025-02-24 |
| 27 | o1 | 3.32 | unverified | 2024-12-05 |
| 28 | Claude Sonnet 4 | 3.11 | unverified | 2025-05-22 |
| 29 | Gemini 2.0 Flash Thinking (Jan 2025) | 1.85 | unverified | 2025-01-21 |
| 30 | Llama 4 Maverick | 0.92 | unverified | 2025-04-05 |
| 31 | GPT-4.5 | 0.67 | unverified | 2025-02-27 |
| 32 | GPT-4.1 | 0.63 | unverified | 2025-04-14 |
| 33 | Amazon Nova Pro | 0 | unverified | 2024-12-03 |
| 34 | Claude 3.5 Sonnet (October 2024) | 0 | unverified | 2024-10-22 |
| 35 | Mistral Medium 3 | 0 | unverified | 2025-05-07 |
| 36 | GPT-4o (Nov 2024) | 0 | unverified | 2024-05-13 |
| 37 | Gemini 1.5 Pro (Sept 2024) | 0 | unverified | 2024-09-24 |