Evals for Every Language - Language ky: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 70.04 |
| 2 | Claude Opus 4.7 | 70 |
| 3 | Claude Opus 4.8 | 69.7 |
| 4 | GPT-5.3 | 68.87 |
| 5 | GPT-5 | 68.76 |
| 6 | GPT-5.2 | 68.46 |
| 7 | Grok 4.20 | 67.41 |
| 8 | GPT-5.1 | 67.2 |
| 9 | Claude Sonnet 4.6 | 66.92 |
| 10 | Qwen 3.6 Plus | 66.82 |
| 11 | GPT-5.4 | 66.78 |
| 12 | GPT-5.5 | 66.7 |
| 13 | Claude Sonnet 4.5 | 66.63 |
| 14 | Gemini 3.1 Flash Lite | 65.39 |
| 15 | Kimi K2 | 65.32 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ky · How It Works · Data refreshed daily, snapshot 2026-09-05.