Evals for Every Language - Danish (da): leaderboard
Average score across evaluation tasks in Danish (da), from Evals for Every Language.
Metric: Average Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 68 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V3.1 | 80.27 | #264 |
| 2 | Gemini 3.1 Pro (Preview) | 79.86 | #58 |
| 3 | Gemini 3.1 Flash Lite | 78.4 | #191 |
| 4 | Claude Sonnet 4.6 | 78.13 | #90 |
| 5 | Claude Opus 4.8 | 77.47 | #37 |
| 6 | Claude Opus 4.7 | 77.44 | #49 |
| 7 | GPT-5.1 | 76.55 | #135 |
| 8 | GPT-5.2 | 76.13 | #110 |
| 9 | GPT-5.3 | 75.96 | #103 |
| 10 | Claude Sonnet 4 | 75.72 | #199 |
| 11 | Grok 4.20 | 75.37 | #175 |
| 12 | GPT-5 | 75.34 | #98 |
| 13 | Gemini 2.5 Pro | 75.19 | #152 |
| 14 | Mistral Medium 3.1 | 75.04 | #408 |
| 15 | GPT-4o | 74.73 | #343 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-da · How It Works · Data refreshed daily, snapshot 2026-10-20.