Evals for Every Language - Language sr: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 76 |
| 2 | Claude Opus 4.7 | 74.76 |
| 3 | Claude Sonnet 4.6 | 74.11 |
| 4 | Gemini 3.1 Flash Lite | 74.03 |
| 5 | Gemini 2.5 Pro | 73.59 |
| 6 | Claude Opus 4.8 | 73.01 |
| 7 | Claude Sonnet 4.5 | 72.89 |
| 8 | Grok 4.20 | 72.04 |
| 9 | GPT-5 | 72.01 |
| 10 | Claude Sonnet 4 | 71.99 |
| 11 | GPT-5.1 | 71.96 |
| 12 | GPT-5.2 | 71.53 |
| 13 | GPT-5.3 | 71.18 |
| 14 | GPT-5.5 | 69.69 |
| 15 | Gemma 3 27B (IT) | 69.58 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-sr · How It Works · Data refreshed daily, snapshot 2026-09-05.