Evals for Every Language - Language lb — leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 72.87 |
| 2 | Gemini 2.5 Pro | 72.67 |
| 3 | GPT-5 | 71.58 |
| 4 | Gemini 3.1 Pro (Preview) | 71.44 |
| 5 | Claude Opus 4.8 | 71.26 |
| 6 | Claude Sonnet 4 | 70.78 |
| 7 | Grok 4.20 | 70.78 |
| 8 | Gemini 3.1 Flash Lite | 70.35 |
| 9 | GPT-5.1 | 69.59 |
| 10 | Claude Opus 4.7 | 69.44 |
| 11 | Claude Sonnet 4.6 | 69.41 |
| 12 | GPT-5.2 | 69.25 |
| 13 | GPT-5.5 | 68.73 |
| 14 | Gemini 2.5 Flash Lite | 68.06 |
| 15 | Qwen 3.6 Plus | 67.99 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-lb · How the rankings work · Data refreshed daily, snapshot 2026-07-22.