Evals for Every Language - Language sn: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 67.47 |
| 2 | GPT-5.5 | 65.56 |
| 3 | Claude Opus 4.7 | 65.37 |
| 4 | Claude Opus 4.8 | 63.7 |
| 5 | GPT-5.4 | 63.39 |
| 6 | GPT-5 | 63.3 |
| 7 | Grok 4.20 | 63.25 |
| 8 | Gemini 3.1 Flash Lite | 62.85 |
| 9 | GPT-5.3 | 62.53 |
| 10 | Gemini 2.5 Pro | 62.2 |
| 11 | DeepSeek V3.1 | 62.11 |
| 12 | Claude Sonnet 4.5 | 61.92 |
| 13 | Claude Sonnet 4.6 | 61.5 |
| 14 | GPT-5.2 | 60.48 |
| 15 | Qwen 3.6 Plus | 59.83 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-sn · How It Works · Data refreshed daily, snapshot 2026-09-05.