EuroEval English NLU - SQuAD: leaderboard

Metric: Reading comprehension Score (%). Source: euroeval.com. 327 models tracked.

Top models

#ModelScore
1Llama 3.1 405B89.95
2Ministral-3-14B-Reasoning-251288.68
3Magistral Small 1.288.59
4Yi 1.5 34B88.19
5Gemma 2 27B88.11
6Mistral Small 3.287.91
7Llama 3.1 70B87.68
8Ministral 3 14B87.45
9aya-23-35B87.4
10Llama 2 70B Base86.97
11Yi-1.5-9B86.89
12gemma-3-27B-pt85.89
13Mistral Small 385.89
14Mistral Small 3.185.64
15Qwen 3 14B85.46

Interactive version: theaggregate.ai/benchmark?slug=euroeval-english-nlu-squad · How It Works · Data refreshed daily, snapshot 2026-09-05.