Evals for Every Language - Language wuu: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 44.94 |
| 2 | Gemini 3.1 Pro (Preview) | 44.53 |
| 3 | Claude Sonnet 4.5 | 44.43 |
| 4 | Gemini 2.5 Pro | 43.98 |
| 5 | Claude Sonnet 4 | 43.33 |
| 6 | Gemini 3.1 Flash Lite | 42.82 |
| 7 | Claude Sonnet 4.6 | 42.66 |
| 8 | Grok 4.20 | 41.99 |
| 9 | GPT-5.3 | 41.93 |
| 10 | DeepSeek V3.2 Exp | 41.55 |
| 11 | Gemma 3 27B (IT) | 41.32 |
| 12 | GPT-5.1 | 40.71 |
| 13 | DeepSeek V3.1 | 40.32 |
| 14 | GPT-5 Mini | 40.28 |
| 15 | Claude Opus 4.8 | 39.92 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-wuu · How It Works · Data refreshed daily, snapshot 2026-09-05.