Evals for Every Language - Uzbek (uz): leaderboard
Average score across evaluation tasks in Uzbek (uz), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 67 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 76.48 | #58 |
| 2 | Claude Sonnet 4 | 76.06 | #199 |
| 3 | Claude Opus 4.7 | 75.93 | #49 |
| 4 | Claude Sonnet 4.6 | 75.61 | #90 |
| 5 | DeepSeek V3.1 | 75.02 | #264 |
| 6 | GPT-5.5 | 74.84 | #31 |
| 7 | Claude Sonnet 4.5 | 74.1 | #142 |
| 8 | GPT-5.2 | 73.9 | #110 |
| 9 | GPT-5.3 | 73.57 | #103 |
| 10 | DeepSeek V3.2 Exp | 72.77 | #234 |
| 11 | Grok 4.20 | 72.51 | #175 |
| 12 | GPT-5.1 | 71.89 | #135 |
| 13 | Qwen 3.6 Plus | 71.85 | #120 |
| 14 | GPT-5 | 71.77 | #98 |
| 15 | Claude Opus 4.8 | 71.71 | #37 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-uz · How It Works · Data refreshed daily, snapshot 2026-10-20.