Evals for Every Language - Language ur: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Flash Lite | 71.55 |
| 2 | Claude Sonnet 4.5 | 71.11 |
| 3 | Claude Opus 4.7 | 70.7 |
| 4 | Gemini 2.5 Pro | 69.83 |
| 5 | Gemini 3.1 Pro (Preview) | 69.63 |
| 6 | GPT-5 | 68.83 |
| 7 | Claude Sonnet 4 | 68.57 |
| 8 | Claude Opus 4.8 | 68.23 |
| 9 | GPT-5.2 | 68.14 |
| 10 | GPT-5.1 | 68.05 |
| 11 | GPT-5.3 | 68.03 |
| 12 | Claude Sonnet 4.6 | 67.93 |
| 13 | Grok 4.20 | 67.46 |
| 14 | DeepSeek V3.1 | 66.68 |
| 15 | GPT-5.5 | 66.35 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-ur · How It Works · Data refreshed daily, snapshot 2026-09-05.