EuroEval Spanish Summarization - Mlsum ES — leaderboard
Metric: Score (%). Source: euroeval.com. 148 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Bielik-11B-v2.3-Instruct | 31.19 |
| 2 | Gemma 3 27B (IT) | 29.68 |
| 3 | Qwen 2.5 72B Instruct | 29.62 |
| 4 | Apertus-70B-Instruct-2509 | 29.34 |
| 5 | granite-4.0-h-micro | 29.33 |
| 6 | Qwen 3 8B (Non-reasoning) | 29.13 |
| 7 | Qwen 3 14B (Non-reasoning) | 29.12 |
| 8 | Tiny Aya Global | 28.88 |
| 9 | Llama 3.1 8B Instruct | 28.87 |
| 10 | Llama 3.3 70B Instruct | 28.82 |
| 11 | Claude Sonnet 4.5 (Non-reasoning) | 28.69 |
| 12 | Qwen 3 30B A3B 2507 Instruct | 28.65 |
| 13 | GPT-4.1 | 28.52 |
| 14 | gemma-4-E2B-it | 28.48 |
| 15 | Gemini 2.5 Flash Lite (Non-reasoning) | 28.32 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-spanish-summarization-mlsum-es · How the rankings work · Data refreshed daily, snapshot 2026-07-22.