Evals for Every Language - Language myv — leaderboard
Metric: Average Score (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 50.07 |
| 2 | Gemini 2.5 Pro | 49.84 |
| 3 | Claude Opus 4.7 | 46.27 |
| 4 | Claude Sonnet 4.5 | 45.99 |
| 5 | Claude Opus 4.8 | 45.05 |
| 6 | Gemini 3.1 Flash Lite | 44.81 |
| 7 | Gemini 2.5 Flash | 43.55 |
| 8 | Qwen 3.6 Plus | 42.59 |
| 9 | Claude Sonnet 4.6 | 42.43 |
| 10 | GPT-5.5 | 41.75 |
| 11 | Claude Sonnet 4 | 41.12 |
| 12 | DeepSeek V3.2 Exp | 40.01 |
| 13 | Gemini 2.5 Flash Lite | 39.19 |
| 14 | GPT-5 | 39.12 |
| 15 | GPT-5.4 | 38.35 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-myv · How the rankings work · Data refreshed daily, snapshot 2026-07-22.