Evals for Every Language - Language fur — leaderboard
Metric: Average Score (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 59.36 |
| 2 | Gemini 3.1 Pro (Preview) | 58.6 |
| 3 | Claude Sonnet 4.5 | 58.36 |
| 4 | Claude Sonnet 4 | 58.21 |
| 5 | Claude Opus 4.8 | 57.19 |
| 6 | Gemini 3.1 Flash Lite | 56.88 |
| 7 | Claude Opus 4.7 | 56.1 |
| 8 | GPT-5.5 | 55.62 |
| 9 | Qwen 3.6 Plus | 54.96 |
| 10 | GPT-5 | 54.66 |
| 11 | GPT-5.4 | 54.44 |
| 12 | GPT-5.1 | 53.46 |
| 13 | Gemini 2.5 Flash | 52.95 |
| 14 | Claude Sonnet 4.6 | 51.81 |
| 15 | Grok 4.20 | 51.5 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-fur · How the rankings work · Data refreshed daily, snapshot 2026-07-22.