Evals for Every Language - Central Kurdish (ckb): leaderboard
Average score across evaluation tasks in Central Kurdish (ckb), 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 | Gemini 3.1 Pro (Preview) | 78.82 | #58 |
| 2 | Claude Opus 4.8 | 76.6 | #37 |
| 3 | Claude Opus 4.7 | 76.07 | #49 |
| 4 | GPT-5.3 | 73.64 | #103 |
| 5 | GPT-5.5 | 72.67 | #31 |
| 6 | Qwen 3.6 Plus | 72.66 | #120 |
| 7 | Gemini 2.5 Pro | 72.42 | #152 |
| 8 | Gemini 3.1 Flash Lite | 71.16 | #191 |
| 9 | Claude Sonnet 4.6 | 70.26 | #90 |
| 10 | Claude Sonnet 4 | 69.74 | #199 |
| 11 | DeepSeek V3.2 Exp | 69.71 | #234 |
| 12 | Grok 4.20 | 69.08 | #175 |
| 13 | Claude Sonnet 4.5 | 69.02 | #142 |
| 14 | DeepSeek V3.1 | 68.8 | #264 |
| 15 | Llama 4 Maverick | 68.36 | #464 |
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-ckb · How It Works · Data refreshed daily, snapshot 2026-10-20.