Evals for Every Language - Language ny: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 69.28 |
| 2 | Claude Opus 4.8 | 66.64 |
| 3 | Claude Opus 4.7 | 66.54 |
| 4 | GPT-5.1 | 65.85 |
| 5 | GPT-5.3 | 65.54 |
| 6 | GPT-5.5 | 64.14 |
| 7 | GPT-5 | 63.97 |
| 8 | Grok 4.20 | 63.77 |
| 9 | Gemini 2.5 Pro | 63.46 |
| 10 | Gemini 3.1 Flash Lite | 63.44 |
| 11 | GPT-5.4 | 63.42 |
| 12 | Claude Sonnet 4.6 | 63.12 |
| 13 | Claude Sonnet 4.5 | 62.7 |
| 14 | GPT-5.2 | 62.3 |
| 15 | Gemini 2.5 Flash Lite | 60.93 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ny · How It Works · Data refreshed daily, snapshot 2026-09-05.