Evals for Every Language - Language kk — leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72.01 |
| 2 | GPT-5.2 | 71.74 |
| 3 | Claude Opus 4.7 | 71.43 |
| 4 | Claude Sonnet 4 | 70.39 |
| 5 | GPT-5.5 | 69.54 |
| 6 | Claude Opus 4.8 | 69.18 |
| 7 | Gemini 3.1 Flash Lite | 69.04 |
| 8 | Qwen 3.6 Plus | 68.95 |
| 9 | Claude Sonnet 4.5 | 68.89 |
| 10 | GPT-5 | 68.49 |
| 11 | Claude Sonnet 4.6 | 68.46 |
| 12 | GPT-5.1 | 68.22 |
| 13 | GPT-5.4 | 67.6 |
| 14 | Grok 4.20 | 67.59 |
| 15 | Gemini 2.5 Pro | 67.38 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-kk · How the rankings work · Data refreshed daily, snapshot 2026-07-22.