Evals for Every Language - Crimean Tatar (crh): leaderboard
Average score across evaluation tasks in Crimean Tatar (crh), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 75.17 | #37 |
| 2 | Claude Sonnet 4.6 | 73.49 | #90 |
| 3 | Claude Opus 4.7 | 72.75 | #49 |
| 4 | Gemini 3.1 Pro (Preview) | 72.55 | #58 |
| 5 | GPT-5 | 71.77 | #98 |
| 6 | Claude Sonnet 4.5 | 70.53 | #142 |
| 7 | Claude Sonnet 4 | 70.22 | #199 |
| 8 | Grok 4.20 | 70.04 | #175 |
| 9 | GPT-5.4 | 69.73 | #79 |
| 10 | GPT-5.1 | 69.47 | #135 |
| 11 | DeepSeek V3.1 | 69.02 | #264 |
| 12 | Gemini 3.1 Flash Lite | 68.71 | #191 |
| 13 | GPT-5.5 | 68.01 | #31 |
| 14 | Gemini 2.5 Pro | 67.92 | #152 |
| 15 | GPT-5.2 | 67.51 | #110 |
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-crh · How It Works · Data refreshed daily, snapshot 2026-10-20.