Evals for Every Language - Language kmb — leaderboard
Metric: Average Score (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 42.26 |
| 2 | Claude Opus 4.7 | 37.11 |
| 3 | Gemini 2.5 Pro | 36.95 |
| 4 | Claude Sonnet 4.5 | 35.85 |
| 5 | Gemini 3.1 Flash Lite | 34.31 |
| 6 | GPT-5.5 | 33.37 |
| 7 | DeepSeek V3.2 Exp | 33.25 |
| 8 | Claude Sonnet 4.6 | 32.45 |
| 9 | Mistral Medium 3.1 | 32.45 |
| 10 | Gemini 2.5 Flash | 32.33 |
| 11 | Claude Opus 4.8 | 31.62 |
| 12 | GPT-5.4 | 30.97 |
| 13 | Command A | 30.39 |
| 14 | Gemma 3 27B (IT) | 30.12 |
| 15 | Llama 4 Maverick | 28.97 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-kmb · How the rankings work · Data refreshed daily, snapshot 2026-07-22.