Evals for Every Language - Serbian (sr): leaderboard
Average score across evaluation tasks in Serbian (sr), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 66 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 80.36 | #58 |
| 2 | Claude Opus 4.7 | 79.55 | #49 |
| 3 | Gemini 3.1 Flash Lite | 78.97 | #191 |
| 4 | Claude Sonnet 4.6 | 78.8 | #90 |
| 5 | Claude Opus 4.8 | 77.48 | #37 |
| 6 | Claude Sonnet 4.5 | 77.34 | #142 |
| 7 | Gemini 2.5 Pro | 77.32 | #152 |
| 8 | Grok 4.20 | 76.78 | #175 |
| 9 | GPT-5 | 76.56 | #98 |
| 10 | Claude Sonnet 4 | 76.56 | #199 |
| 11 | GPT-5.1 | 76.38 | #135 |
| 12 | GPT-5.2 | 76.05 | #110 |
| 13 | GPT-5.3 | 75.12 | #103 |
| 14 | Gemma 3 27B (IT) | 74.01 | #523 |
| 15 | Mistral Medium 3.1 | 73.68 | #408 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-sr · How It Works · Data refreshed daily, snapshot 2026-10-20.