EuroEval English Summarization - CNN Dailymail — leaderboard
Metric: Score (%). Source: euroeval.com. 151 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Ministral 3 14B | 46.05 |
| 2 | Granite 4.0 Micro | 45.11 |
| 3 | Apertus-70B-Instruct-2509 | 44.93 |
| 4 | Bielik-11B-v2.3-Instruct | 44.64 |
| 5 | Ministral 3 8B | 43.94 |
| 6 | granite-4.0-h-micro | 43.85 |
| 7 | Claude Sonnet 4.5 (Thinking) | 43.73 |
| 8 | Llama 3.3 70B Instruct | 43.69 |
| 9 | Llama 3.1 8B Instruct | 43.69 |
| 10 | Gemini 2.5 Flash Lite (Thinking) | 43.57 |
| 11 | GPT-4.1 | 43.54 |
| 12 | Qwen 3 14B (Non-reasoning) | 43.31 |
| 13 | Claude Haiku 4.5 (20251001) | 43.09 |
| 14 | Gemini 2.5 Flash Lite (Non-reasoning) | 42.99 |
| 15 | GPT-5 Mini | 42.94 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-english-summarization-cnn-dailymail · How the rankings work · Data refreshed daily, snapshot 2026-07-22.