EuroEval Danish Common Sense Reasoning — leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 357 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Non-reasoning) | 90.41 |
| 2 | Claude Sonnet 4.5 (Thinking) | 90.1 |
| 3 | Qwen 3 235B A22B 2507 Instruct | 85 |
| 4 | Gemini 3 Pro (Preview) | 84.75 |
| 5 | Claude Sonnet 4.6 | 83.34 |
| 6 | Mistral Small 3.1 | 82.2 |
| 7 | GLM-4.7 FP8 | 81.97 |
| 8 | Gemma 4 31B (IT) | 81.9 |
| 9 | Gemini 3 Flash (Preview) (Non-reasoning) | 81.88 |
| 10 | GPT-5 (Minimal) | 81.15 |
| 11 | GPT-5 (High) | 80.61 |
| 12 | GPT-5 | 80.36 |
| 13 | Qwen 3 Next 80B A3B Instruct | 80.24 |
| 14 | Gemini 2.5 Pro | 78.89 |
| 15 | Llama 3.1 405B Instruct FP8 | 78.34 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-danish-common-sense-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.