Evals for Every Language - Language rn: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 64.86 |
| 2 | Claude Sonnet 4.6 | 64.19 |
| 3 | Claude Opus 4.8 | 64.01 |
| 4 | GPT-5.3 | 63.52 |
| 5 | GPT-5.5 | 61.71 |
| 6 | GPT-5.2 | 61.54 |
| 7 | Claude Opus 4.7 | 61.46 |
| 8 | Gemini 2.5 Pro | 60.56 |
| 9 | Grok 4.20 | 60.34 |
| 10 | Claude Sonnet 4.5 | 59.98 |
| 11 | GPT-5.4 | 59.8 |
| 12 | GPT-5 | 59.03 |
| 13 | Gemini 3.1 Flash Lite | 58.87 |
| 14 | Qwen 3.6 Plus | 57.92 |
| 15 | GPT-5.1 | 57.25 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-rn · How It Works · Data refreshed daily, snapshot 2026-09-05.