Evals for Every Language - Language fon — leaderboard
Metric: Average Score (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 42.48 |
| 2 | Claude Opus 4.7 | 38.05 |
| 3 | Gemini 2.5 Pro | 35.48 |
| 4 | Gemini 3.1 Flash Lite | 34.41 |
| 5 | GPT-5.4 | 32.99 |
| 6 | Claude Sonnet 4.5 | 31.77 |
| 7 | Claude Sonnet 4.6 | 31.65 |
| 8 | GPT-5.5 | 31.45 |
| 9 | Claude Opus 4.8 | 31.19 |
| 10 | Qwen 3.6 Plus | 30.59 |
| 11 | Gemini 2.5 Flash | 29.52 |
| 12 | Llama 4 Maverick | 29.33 |
| 13 | Grok 4.20 | 28.5 |
| 14 | Claude Sonnet 4 | 28.35 |
| 15 | Mistral Medium 3.1 | 27.2 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-fon · How the rankings work · Data refreshed daily, snapshot 2026-07-22.