Evals for Every Language - Language hr: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 74.28 |
| 2 | Claude Sonnet 4.6 | 72.85 |
| 3 | Claude Opus 4.7 | 72.71 |
| 4 | Gemini 2.5 Pro | 72.65 |
| 5 | Claude Sonnet 4.5 | 72.4 |
| 6 | GPT-5.2 | 72.38 |
| 7 | GPT-5.3 | 71.44 |
| 8 | Gemini 3.1 Flash Lite | 71.41 |
| 9 | GPT-5 | 71.21 |
| 10 | GPT-5.1 | 71.08 |
| 11 | Claude Sonnet 4 | 70.98 |
| 12 | Claude Opus 4.8 | 70.94 |
| 13 | Grok 4.20 | 69.63 |
| 14 | jamba-large-1.7 | 69.63 |
| 15 | Mistral Medium 3.1 | 69.06 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-hr · How It Works · Data refreshed daily, snapshot 2026-09-05.