Evals for Every Language - Language id: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 74.98 |
| 2 | Gemini 3.1 Pro (Preview) | 74.66 |
| 3 | Claude Opus 4.8 | 74.47 |
| 4 | Claude Opus 4.7 | 74.12 |
| 5 | Gemini 3.1 Flash Lite | 73.88 |
| 6 | Claude Sonnet 4.6 | 73.48 |
| 7 | Gemini 2.5 Pro | 72.67 |
| 8 | GPT-5.3 | 72.36 |
| 9 | GPT-5.2 | 72.26 |
| 10 | Claude Sonnet 4 | 71.85 |
| 11 | GPT-5 | 71.33 |
| 12 | GPT-5.1 | 71.01 |
| 13 | DeepSeek V3.2 Exp | 70.66 |
| 14 | Qwen 3.6 Plus | 70.62 |
| 15 | Command A | 70.35 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-id · How It Works · Data refreshed daily, snapshot 2026-09-05.