Evals for Every Language - Language ee: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 63.86 |
| 2 | Claude Opus 4.7 | 60.86 |
| 3 | Gemini 3.1 Flash Lite | 57.63 |
| 4 | Claude Opus 4.8 | 57.06 |
| 5 | GPT-5.5 | 56.99 |
| 6 | Gemini 2.5 Pro | 53.47 |
| 7 | Claude Sonnet 4 | 52.53 |
| 8 | Claude Sonnet 4.5 | 52.09 |
| 9 | GPT-5.4 | 51.95 |
| 10 | Qwen 3.6 Plus | 51.92 |
| 11 | Claude Sonnet 4.6 | 51.37 |
| 12 | GPT-5.3 | 47.79 |
| 13 | Grok 4.20 | 47.55 |
| 14 | DeepSeek V3.1 | 45.91 |
| 15 | GPT-5.2 | 44.45 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ee · How It Works · Data refreshed daily, snapshot 2026-09-05.