Evals for Every Language - Language hne — leaderboard
Metric: Average Score (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 51.52 |
| 2 | Gemini 3.1 Pro (Preview) | 50.91 |
| 3 | Gemini 2.5 Pro | 50.37 |
| 4 | GPT-5.4 | 48.55 |
| 5 | GPT-5.1 | 48.09 |
| 6 | Gemini 2.5 Flash Lite | 47.41 |
| 7 | GPT-5.5 | 47.35 |
| 8 | Claude Sonnet 4.6 | 47.31 |
| 9 | Claude Sonnet 4.5 | 46.74 |
| 10 | Claude Sonnet 4 | 46.64 |
| 11 | GPT-4o | 46.21 |
| 12 | Nova Pro (v1) | 46.15 |
| 13 | Gemini 2.5 Flash | 45.9 |
| 14 | Command A | 45.8 |
| 15 | Gemini 3.1 Flash Lite | 44.92 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-hne · How the rankings work · Data refreshed daily, snapshot 2026-07-22.