Evals for Every Language - Kurdish (ku): leaderboard
Average score across evaluation tasks in Kurdish (ku), 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) | 75.55 | #58 |
| 2 | Grok 4.20 | 73.81 | #175 |
| 3 | Claude Opus 4.8 | 73.53 | #37 |
| 4 | GPT-5.3 | 73.49 | #103 |
| 5 | Gemini 3.1 Flash Lite | 72.6 | #191 |
| 6 | Claude Opus 4.7 | 72.49 | #49 |
| 7 | GPT-5.2 | 70.72 | #110 |
| 8 | Claude Sonnet 4.5 | 70.33 | #142 |
| 9 | GPT-5.1 | 70.28 | #135 |
| 10 | GPT-5 | 69.89 | #98 |
| 11 | Claude Sonnet 4.6 | 69.82 | #90 |
| 12 | Qwen 3.6 Flash | 69.05 | #214 |
| 13 | Qwen 3.6 Plus | 68.79 | #120 |
| 14 | GPT-5.4 | 68.61 | #79 |
| 15 | GPT-5.5 | 68.44 | #31 |
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-ku · How It Works · Data refreshed daily, snapshot 2026-10-20.