EuroEval Italian Summarization - Ilpost SUM — leaderboard
Metric: Score (%). Source: euroeval.com. 151 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Mistral Small 3.1 | 39.2 |
| 2 | gemma-4-E2B-it | 38.97 |
| 3 | gemma-4-E4B-it | 38.85 |
| 4 | GPT-4.1 | 38.72 |
| 5 | Apertus-70B-Instruct-2509 | 38.7 |
| 6 | Bielik-11B-v2.3-Instruct | 38.66 |
| 7 | Gemma 3 12B (IT) | 38.63 |
| 8 | Qwen 3 14B (Non-reasoning) | 38.58 |
| 9 | Qwen 3 8B (Non-reasoning) | 38.55 |
| 10 | Gemma 3 27B (IT) | 38.42 |
| 11 | Gemma 4 26B A4B (IT) | 38.42 |
| 12 | Gemma 4 31B (IT) | 38.37 |
| 13 | GPT-5.4 Mini (Non-reasoning) | 38.35 |
| 14 | Mistral Small 3.2 | 38.3 |
| 15 | Gemma 3n E4B (IT) | 38.28 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-italian-summarization-ilpost-sum · How the rankings work · Data refreshed daily, snapshot 2026-07-22.