Evals for Every Language - Azerbaijani (az): leaderboard
Average score across evaluation tasks in Azerbaijani (az), 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) | 75.04 | #58 |
| 2 | Gemini 3.1 Flash Lite | 74.43 | #191 |
| 3 | GPT-4o | 71.79 | #343 |
| 4 | Gemini 2.5 Pro | 71.38 | #152 |
| 5 | Claude Sonnet 4 | 71.34 | #199 |
| 6 | Claude Opus 4.8 | 71.32 | #37 |
| 7 | GPT-5.5 | 71.3 | #31 |
| 8 | GPT-5.1 | 71.25 | #135 |
| 9 | Claude Opus 4.7 | 71.15 | #49 |
| 10 | Claude Sonnet 4.5 | 71 | #142 |
| 11 | GPT-5 | 70.9 | #98 |
| 12 | Claude Sonnet 4.6 | 70.64 | #90 |
| 13 | Qwen 3.6 Plus | 70.61 | #120 |
| 14 | DeepSeek V3.2 Exp | 70.57 | #234 |
| 15 | Nova Pro (v1) | 70.26 | #497 |
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-az · How It Works · Data refreshed daily, snapshot 2026-10-20.