Evals for Every Language - Language sk: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.8 | 73.72 |
| 2 | Gemini 3.1 Pro (Preview) | 72.66 |
| 3 | Gemini 2.5 Pro | 72.45 |
| 4 | Claude Opus 4.7 | 72.44 |
| 5 | Claude Sonnet 4.5 | 71.98 |
| 6 | GPT-5.1 | 71.07 |
| 7 | GPT-5 | 70.92 |
| 8 | Grok 4.20 | 70.81 |
| 9 | DeepSeek V3.1 | 70.29 |
| 10 | Gemini 3.1 Flash Lite | 69.29 |
| 11 | GPT-5.3 | 69.05 |
| 12 | Claude Sonnet 4 | 69.04 |
| 13 | GPT-5.5 | 68.83 |
| 14 | Claude Sonnet 4.6 | 68.61 |
| 15 | Mistral Medium 3.1 | 68.31 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-sk · How It Works · Data refreshed daily, snapshot 2026-09-05.