EuroEval Polish Summarization - PSC — leaderboard
Metric: Score (%). Source: euroeval.com. 148 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Ministral-3-3B-Instruct-2512 | 25.82 |
| 2 | Ministral-3-8B-Instruct-2512 | 25.67 |
| 3 | GPT-5.4 Nano (Non-reasoning) | 25.44 |
| 4 | GPT-OSS-20B (Low) | 25.36 |
| 5 | GPT-OSS-20B (Medium) | 25.35 |
| 6 | GPT-5.4 Nano (High) | 25.24 |
| 7 | GPT-5.4 Nano (Medium) | 25.21 |
| 8 | LFM2 1.2B | 25.18 |
| 9 | Apertus-70B-Instruct-2509 | 25.01 |
| 10 | Ministral-3-14B-Instruct-2512 | 24.73 |
| 11 | Bielik-11B-v2.3-Instruct | 24.62 |
| 12 | Claude Haiku 4.5 (20251001) | 24.61 |
| 13 | Qwen 3 1.7B (Non-reasoning) | 24.52 |
| 14 | GPT-5 Nano | 24.36 |
| 15 | Qwen 3 30B A3B 2507 Instruct | 24.19 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-polish-summarization-psc · How the rankings work · Data refreshed daily, snapshot 2026-07-22.