Evals for Every Language - Language mi — leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72.69 |
| 2 | Gemini 3.1 Flash Lite | 69.35 |
| 3 | GPT-5 | 68.22 |
| 4 | GPT-5.5 | 67.33 |
| 5 | Gemini 2.5 Pro | 67.02 |
| 6 | Claude Sonnet 4.6 | 66.98 |
| 7 | Qwen 3.6 Plus | 66.57 |
| 8 | GPT-4o | 66.35 |
| 9 | Grok 4.20 | 66.34 |
| 10 | Claude Sonnet 4.5 | 66.32 |
| 11 | GPT-5.1 | 66.07 |
| 12 | GPT-5.2 | 65.79 |
| 13 | GPT-5.4 | 65.68 |
| 14 | Claude Opus 4.7 | 64.84 |
| 15 | Claude Opus 4.8 | 64.43 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-mi · How the rankings work · Data refreshed daily, snapshot 2026-07-22.