Evals for Every Language - Language mk: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 74.29 |
| 2 | Gemini 3.1 Flash Lite | 72.65 |
| 3 | Claude Sonnet 4.6 | 72.47 |
| 4 | Claude Sonnet 4.5 | 72.33 |
| 5 | GPT-5.5 | 72.02 |
| 6 | Claude Sonnet 4 | 71.74 |
| 7 | GPT-5.3 | 70.51 |
| 8 | Gemini 2.5 Pro | 70.48 |
| 9 | Qwen 3.6 Plus | 70.45 |
| 10 | GPT-4o | 70.44 |
| 11 | Claude Opus 4.7 | 70.34 |
| 12 | Claude Haiku 4.5 | 69.99 |
| 13 | GPT-5 | 69.93 |
| 14 | GPT-5.1 | 69.66 |
| 15 | Claude Opus 4.8 | 69.61 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-mk · How It Works · Data refreshed daily, snapshot 2026-09-05.