Evals for Every Language - Language tyv — leaderboard
Metric: Average Score (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 51.21 |
| 2 | Claude Opus 4.7 | 47.37 |
| 3 | Gemini 3.1 Pro (Preview) | 46.68 |
| 4 | Gemini 2.5 Flash | 45.76 |
| 5 | Claude Sonnet 4.5 | 45.46 |
| 6 | Claude Sonnet 4.6 | 44.06 |
| 7 | Qwen 3.6 Plus | 43.31 |
| 8 | Claude Sonnet 4 | 42.52 |
| 9 | GPT-5.5 | 40.9 |
| 10 | Gemini 2.5 Flash Lite | 40.53 |
| 11 | Claude Opus 4.8 | 40.14 |
| 12 | Nova Pro (v1) | 39.35 |
| 13 | DeepSeek V3.2 Exp | 39.22 |
| 14 | GPT-5.1 | 39.04 |
| 15 | Gemini 3.1 Flash Lite | 38.9 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-tyv · How the rankings work · Data refreshed daily, snapshot 2026-07-22.