Evals for Every Language - Language da: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 76.85 |
| 2 | DeepSeek V3.1 | 76.78 |
| 3 | Gemini 3.1 Flash Lite | 75.1 |
| 4 | Claude Sonnet 4.6 | 74.59 |
| 5 | Claude Opus 4.8 | 74.57 |
| 6 | Claude Opus 4.7 | 74.47 |
| 7 | GPT-5.1 | 73.53 |
| 8 | Gemini 2.5 Pro | 73.21 |
| 9 | GPT-5.2 | 73.04 |
| 10 | GPT-5.3 | 72.93 |
| 11 | Claude Sonnet 4 | 72.37 |
| 12 | GPT-4o | 72.2 |
| 13 | GPT-5 | 72.17 |
| 14 | Grok 4.20 | 71.83 |
| 15 | Qwen 3.6 Plus | 71.82 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-da · How It Works · Data refreshed daily, snapshot 2026-09-05.