EuroEval Danish Knowledge - Danish Citizen Tests: leaderboard
Multiple-choice questions from the Danish citizenship and permanent-residence tests. One of the two datasets averaged into EuroEval's knowledge score for this language; few-shot by default, with some zero-shot and validation-split runs; Matthews correlation x100 as the primary metric (signed, chance 0), higher is better.
Metric: MCC (x100). Source: euroeval.com. Saturation forecast: Estimated already saturated. 454 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 100 | #159 |
| 2 | GPT-5 | 100 | #105 |
| 3 | Gemini 3 Pro (Preview) | 100 | #71 |
| 4 | Gemini 2.5 Pro (Preview 03-25) | 100 | #126 |
| 5 | Claude Sonnet 4.5 (Thinking) | 100 | #148 (Claude Sonnet 4.5) |
| 6 | O3 (2025-04-16) | 100 | #125 |
| 7 | Gemini 3.1 Flash Lite (Preview) | 100 | #201 |
| 8 | Gemini 2.5 Flash (Preview 04-17) | 100 | #246 |
| 9 | Gemini 2.5 Flash (Thinking) | 100 | #255 (Gemini 2.5 Flash) |
| 10 | Gemini 3 Flash (Preview) (Thinking) | 100 | #90 (Gemini 3 Flash (Preview)) |
| 11 | GPT-5 (2025-08-07) (High) | 100 | |
| 12 | Claude 3.7 Sonnet (20250219) (Thinking) | 100 | #209 (Claude 3.7 Sonnet (20250219)) |
| 13 | Gemini 3 Flash (Preview) (Non-reasoning) | 98.84 | #90 (Gemini 3 Flash (Preview)) |
| 14 | GPT-5.2 | 98.83 | #115 |
| 15 | Gemini 2.5 Flash (Non-reasoning) | 98.35 | #255 (Gemini 2.5 Flash) |
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-danish-citizen-tests · How It Works · Data refreshed daily, snapshot 2026-11-05.