EuroEval Polish Summarization - PSC: leaderboard

Metric: Score (%). Source: euroeval.com. 148 models tracked.

Top models

#ModelScore
1Ministral-3-3B-Instruct-251225.82
2Ministral-3-8B-Instruct-251225.67
3GPT-OSS-20B (Low)25.36
4GPT-OSS-20B (Medium)25.35
5GPT-5.4 Nano (High)25.24
6GPT-5.4 Nano (Medium)25.21
7LFM2 1.2B25.18
8Apertus-70B-Instruct-250925.01
9Ministral-3-14B-Instruct-251224.73
10Claude Haiku 4.5 (20251001)24.61
11GPT-5 Nano24.36
12Qwen 3 30B A3B 2507 Instruct24.19
13GPT-5.224.17
14Qwen 2.5 72B Instruct24.16
15Ministral-3-3B-Reasoning-251223.95

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