Evals for Every Language - Language uz: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72.09 |
| 2 | Claude Opus 4.7 | 71.37 |
| 3 | Claude Sonnet 4.6 | 70.79 |
| 4 | Claude Sonnet 4 | 70.7 |
| 5 | Claude Sonnet 4.5 | 70.3 |
| 6 | GPT-5.5 | 70.08 |
| 7 | DeepSeek V3.1 | 69.84 |
| 8 | GPT-5.2 | 69.04 |
| 9 | GPT-5.3 | 68.63 |
| 10 | Claude Opus 4.8 | 68.11 |
| 11 | Qwen 3.6 Plus | 68.01 |
| 12 | Grok 4.20 | 67.78 |
| 13 | GPT-5.1 | 67.64 |
| 14 | DeepSeek V3.2 Exp | 67.39 |
| 15 | GPT-5 | 67.35 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-uz · How It Works · Data refreshed daily, snapshot 2026-09-05.