Evals for Every Language - Language nqo — leaderboard
Metric: Average Score (%). Source: huggingface.co. 70 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 48.98 |
| 2 | Claude Opus 4.8 | 47.89 |
| 3 | Claude Sonnet 4.5 | 46.56 |
| 4 | Claude Sonnet 4 | 42.67 |
| 5 | Gemini 3.1 Flash Lite | 41.82 |
| 6 | Gemini 2.5 Pro | 41.02 |
| 7 | GPT-5.4 | 40.42 |
| 8 | GPT-5.5 | 38.6 |
| 9 | DeepSeek V3.2 Exp | 36.75 |
| 10 | Gemini 3.1 Pro (Preview) | 35.98 |
| 11 | GLM 4.5 Air | 35.97 |
| 12 | Qwen 3.6 Plus | 35.48 |
| 13 | Nova Pro (v1) | 33.8 |
| 14 | Grok 4.20 | 33.66 |
| 15 | Claude Sonnet 4.6 | 33.05 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-nqo · How the rankings work · Data refreshed daily, snapshot 2026-07-22.