EuroEval Danish NLU - Multi Wiki QA DA — leaderboard

Metric: Reading comprehension Score (%). Source: euroeval.com. 270 models tracked.

Top models

#ModelScore
1Ministral 3 14B82.94
2Mistral Small 3.282.73
3Magistral Small82.72
4SOLAR-10.7B-v1.082.34
5Qwen 3 14B (Non-reasoning)82.01
6gemma-3-27B-pt81.81
7Bielik-11B-v2.3-Instruct81.65
8Ministral-3-14B-Reasoning-251280.83
9Llama 3.1 70B80.7
10Mistral Small 3.180.39
11Qwen 2.5 72B Instruct79.64
12GPT-5.4 Mini (Non-reasoning)79.41
13Ministral 3 8B79.12
14Ministral 3 3B79.06
15Llama 3.1 8B78.62

Interactive version: theaggregate.ai/benchmark?slug=euroeval-danish-nlu-multi-wiki-qa-da · How the rankings work · Data refreshed daily, snapshot 2026-07-22.