EuroEval Danish NLU - Dansk: leaderboard
The "Dansk" subtask of EuroEval Danish NLU. Danish-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Micro F1 excluding MISC (%). Source: euroeval.com. Saturation forecast: Around January 2027. 432 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.7 Sonnet (20250219) (Thinking) | 72.62 | #201 (Claude 3.7 Sonnet (20250219)) |
| 2 | Gemma 4 31B (IT) | 71.39 | #176 |
| 3 | O3 (2025-04-16) | 71.31 | #121 |
| 4 | GPT-5.4 Mini (2026-03-17) (High) | 71.15 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 70.88 | #82 (Gemini 3 Flash (Preview)) |
| 6 | GPT-5 | 70.37 | #98 |
| 7 | GLM-4.7 FP8 | 70.24 | #209 |
| 8 | Claude Sonnet 4.5 (Thinking) | 69.94 | #142 (Claude Sonnet 4.5) |
| 9 | GPT-5 (2025-08-07) (High) | 69.74 | |
| 10 | Gemini 3.1 Flash Lite (Preview) | 69.38 | #194 |
| 11 | Qwen 3.5 27B FP8 | 69.18 | #164 |
| 12 | Qwen 3 4B 2507 (Thinking) | 68.78 | #538 (Qwen 3 4B 2507) |
| 13 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 68.35 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 14 | Llama 3.1 405B Instruct FP8 | 68.29 | #389 |
| 15 | Gemini 3 Pro (Preview) | 68.07 | #66 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-danish-nlu-dansk · How It Works · Data refreshed daily, snapshot 2026-10-20.