Evals for Every Language - Language eu: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 70.81 |
| 2 | GPT-5.3 | 69.97 |
| 3 | Gemini 2.5 Pro | 69.5 |
| 4 | Claude Sonnet 4.5 | 69.36 |
| 5 | Gemini 3.1 Flash Lite | 69.27 |
| 6 | Claude Sonnet 4.6 | 69.26 |
| 7 | Claude Opus 4.7 | 68.46 |
| 8 | GPT-4o | 68.23 |
| 9 | Grok 4.20 | 68.06 |
| 10 | Claude Sonnet 4 | 67.83 |
| 11 | GPT-5.5 | 67.59 |
| 12 | GPT-5.1 | 67.47 |
| 13 | GPT-5 | 67.4 |
| 14 | GPT-4.1 | 67.3 |
| 15 | DeepSeek V3.1 | 67.26 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-eu · How It Works · Data refreshed daily, snapshot 2026-09-05.