Evals for Every Language - Classification: leaderboard
Metric: Average Score (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 98.87 |
| 2 | Claude Sonnet 4.5 | 98.87 |
| 3 | Gemini 3.1 Pro (Preview) | 98.25 |
| 4 | Claude Sonnet 4 | 97.84 |
| 5 | GPT-4o | 96.86 |
| 6 | GPT-5 | 96.75 |
| 7 | Claude Opus 4.7 | 95.98 |
| 8 | GPT-5.1 | 95.98 |
| 9 | GPT-5.3 | 95.57 |
| 10 | Gemini 3.1 Flash Lite | 95.5 |
| 11 | Gemma 3 27B (IT) | 95.41 |
| 12 | Command A | 95.36 |
| 13 | Nova Pro (v1) | 95.21 |
| 14 | Mistral Medium 3.1 | 94.48 |
| 15 | GPT-3.5 Turbo | 92.22 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-classification · How It Works · Data refreshed daily, snapshot 2026-09-05.