Evals for Every Language - Language it — leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 73.92 |
| 2 | Gemini 3.1 Pro (Preview) | 73.73 |
| 3 | Claude Opus 4.8 | 73.72 |
| 4 | Claude Sonnet 4.5 | 73.44 |
| 5 | Claude Sonnet 4.6 | 72.96 |
| 6 | Claude Sonnet 4 | 72.95 |
| 7 | GPT-5.1 | 72.95 |
| 8 | Grok 4.20 | 72.51 |
| 9 | Gemini 3.1 Flash Lite | 71.75 |
| 10 | Gemini 2.5 Pro | 71.59 |
| 11 | Claude Haiku 4.5 | 71.57 |
| 12 | GPT-5.2 | 71.29 |
| 13 | Mistral Medium 3.1 | 71.25 |
| 14 | Qwen 3.6 Plus | 71.11 |
| 15 | GPT-5 | 70.86 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-it · How the rankings work · Data refreshed daily, snapshot 2026-07-22.