Evals for Every Language - Language nn — leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 64.37 |
| 2 | Gemini 3.1 Flash Lite | 62.33 |
| 3 | Claude Opus 4.7 | 61.83 |
| 4 | Gemini 2.5 Flash Lite | 61.69 |
| 5 | Claude Sonnet 4 | 61.58 |
| 6 | Claude Sonnet 4.6 | 61.5 |
| 7 | Claude Sonnet 4.5 | 61.46 |
| 8 | Claude Opus 4.8 | 61.35 |
| 9 | GPT-5 | 61.17 |
| 10 | Gemini 2.5 Pro | 60.84 |
| 11 | GPT-4o | 60.74 |
| 12 | GPT-5.1 | 59.79 |
| 13 | Mistral Medium 3.1 | 59.47 |
| 14 | GPT-5.4 | 59.32 |
| 15 | Gemma 3 27B (IT) | 58.53 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-nn · How the rankings work · Data refreshed daily, snapshot 2026-07-22.