Evals for Every Language - French (fr): leaderboard
Average score across evaluation tasks in French (fr), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 82.15 | #58 |
| 2 | Claude Opus 4.8 | 82.06 | #37 |
| 3 | Claude Opus 4.7 | 82.02 | #49 |
| 4 | GPT-5.5 | 81.59 | #31 |
| 5 | GPT-5 | 81.5 | #98 |
| 6 | Gemini 2.5 Pro | 81.11 | #152 |
| 7 | Grok 4.20 | 80.78 | #175 |
| 8 | Claude Sonnet 4.5 | 80.68 | #142 |
| 9 | GPT-5.3 | 80.64 | #103 |
| 10 | Claude Haiku 4.5 | 80.49 | #280 |
| 11 | GPT-5.2 | 80.36 | #110 |
| 12 | Gemini 3.1 Flash Lite | 79.28 | #191 |
| 13 | GPT-5.1 | 79.06 | #135 |
| 14 | Mistral Medium 3.1 | 78.7 | #408 |
| 15 | GPT-4.1 | 78.06 | #248 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-fr · How It Works · Data refreshed daily, snapshot 2026-10-20.