Evals for Every Language - Language gn: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 67.45 |
| 2 | Claude Opus 4.7 | 65.2 |
| 3 | GPT-5.3 | 64.45 |
| 4 | Claude Opus 4.8 | 64.37 |
| 5 | GPT-5.5 | 64.25 |
| 6 | Gemini 2.5 Pro | 63.5 |
| 7 | GPT-5.4 | 62 |
| 8 | Gemini 3.1 Flash Lite | 61.84 |
| 9 | Grok 4.20 | 60.81 |
| 10 | GPT-5 | 60.74 |
| 11 | Qwen 3.6 Plus | 59.08 |
| 12 | Claude Sonnet 4.5 | 58.89 |
| 13 | GPT-5.2 | 57.43 |
| 14 | Claude Sonnet 4.6 | 55.91 |
| 15 | GPT-5.1 | 55.1 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-gn · How It Works · Data refreshed daily, snapshot 2026-09-05.