HumainE Leaderboard — leaderboard
Metric: HumainE Score. Source: huggingface.co. 53 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 35.38 |
| 2 | Gemini 3.5 Flash | 34.81 |
| 3 | Gemini 3 Pro | 33.8 |
| 4 | Claude Fable 5 | 33.52 |
| 5 | Grok 4.20 | 33.32 |
| 6 | Gemini 2.5 Pro | 33.23 |
| 7 | Qwen 3.7 Max | 33.03 |
| 8 | Mistral Large 3 | 32.68 |
| 9 | DeepSeek V4 Flash | 32.39 |
| 10 | Qwen 3 235B A22B 2507 | 32.16 |
| 11 | Claude Opus 4.7 | 31.76 |
| 12 | DeepSeek V4 Pro | 31.05 |
| 13 | DeepSeek V3 (0324) | 30.95 |
| 14 | Magistral Medium | 30.88 |
| 15 | GPT-5.4 | 30.4 |
Interactive version: aibenchmarks.dev/benchmark?slug=humaine-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-17.