EuroEval Danish Knowledge: leaderboard
EuroEval's Danish knowledge task — multiple-choice general-knowledge questions in Danish, from the EuroEval European language model benchmark suite.
Metric: Knowledge Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 435 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) (Thinking) | 99.25 | #82 (Gemini 3 Flash (Preview)) |
| 2 | Gemini 2.5 Pro | 97.56 | #152 |
| 3 | Gemini 3 Flash (Preview) (Non-reasoning) | 96.96 | #82 (Gemini 3 Flash (Preview)) |
| 4 | O3 (2025-04-16) | 96.72 | #121 |
| 5 | Gemini 2.5 Pro (Preview 03-25) | 96.26 | #123 |
| 6 | Gemini 2.5 Flash (Thinking) | 96.25 | #245 (Gemini 2.5 Flash) |
| 7 | GPT-5 (2025-08-07) (High) | 95.41 | |
| 8 | Claude Sonnet 4.6 | 95.15 | #90 |
| 9 | GPT-5 | 94.88 | #98 |
| 10 | Gemini 3 Pro (Preview) | 94.81 | #66 |
| 11 | Gemini 2.5 Flash (Preview 04-17) | 94.46 | #237 |
| 12 | GPT-4.1 | 94.06 | #248 |
| 13 | Llama 3.1 70B Instruct | 93.85 | #561 |
| 14 | Llama 3.3 70B Instruct | 93.65 | #534 |
| 15 | GPT-5.4 Mini (2026-03-17) (High) | 93.64 | #169 (GPT-5.4 Mini (2026-03-17)) |
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-knowledge · How It Works · Data refreshed daily, snapshot 2026-10-20.