EuroEval Catalan NLU - MultiWikiQA CA — leaderboard

Metric: Reading comprehension Score (%). Source: euroeval.com. 212 models tracked.

Top models

#ModelScore
1Ministral 3 3B78.35
2SOLAR-10.7B-v1.078.2
3Mistral Small 3.277.99
4gemma-3-12B-pt77.7
5Olmo 3.1 32B Instruct77.23
6Ministral-3-14B-Reasoning-251276.9
7Qwen 3 14B (Non-reasoning)76.65
8Bielik-11B-v2.3-Instruct76.56
9Mistral Small 3.175.96
10Llama 3.1 70B75.86
11Ministral 3 14B74.48
12Ministral-3-3B-Reasoning-251274.41
13Qwen 3 8B (Non-reasoning)74.17
14gemma-3-27B-pt74.03
15Llama 3.1 8B73.75

Interactive version: theaggregate.ai/benchmark?slug=euroeval-catalan-nlu-multiwikiqa-ca · How the rankings work · Data refreshed daily, snapshot 2026-07-22.