Evals for Every Language - Language fuv: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 35.29 |
| 2 | Claude Opus 4.7 | 33.79 |
| 3 | Claude Sonnet 4 | 32.19 |
| 4 | GPT-5.5 | 31.26 |
| 5 | Gemini 2.5 Pro | 30.11 |
| 6 | GPT-5.4 | 29.08 |
| 7 | Claude Sonnet 4.6 | 28.59 |
| 8 | GPT-5 | 28.46 |
| 9 | GPT-5.3 | 28.46 |
| 10 | Grok 4.20 | 28.44 |
| 11 | Gemini 2.5 Flash | 28.37 |
| 12 | Qwen 3.6 Plus | 28.13 |
| 13 | GPT-5.2 | 27.69 |
| 14 | Claude Sonnet 4.5 | 27.47 |
| 15 | Claude Opus 4.8 | 27.21 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-fuv · How It Works · Data refreshed daily, snapshot 2026-09-05.