Evals for Every Language - Language ln: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 66.34 |
| 2 | Claude Opus 4.7 | 65.2 |
| 3 | Gemini 3.1 Flash Lite | 64.78 |
| 4 | Claude Opus 4.8 | 63.82 |
| 5 | GPT-5 | 63.02 |
| 6 | Gemini 2.5 Pro | 62.29 |
| 7 | GPT-5.5 | 61.06 |
| 8 | GPT-5.4 | 60.56 |
| 9 | GPT-5.3 | 60.15 |
| 10 | GPT-5.1 | 59.27 |
| 11 | Claude Sonnet 4.5 | 59.17 |
| 12 | GPT-5.2 | 58.99 |
| 13 | Claude Sonnet 4 | 58.66 |
| 14 | GPT-4o | 57.62 |
| 15 | Claude Sonnet 4.6 | 57.12 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ln · How It Works · Data refreshed daily, snapshot 2026-09-05.