EuroEval Estonian Summarization - ERR News: leaderboard
Metric: Score (%). Source: euroeval.com. 150 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.3 70B Instruct | 32.83 |
| 2 | Gemma 3 27B (IT) | 32.33 |
| 3 | Mistral Small 3.1 | 32.23 |
| 4 | Gemma 3 12B (IT) | 32.17 |
| 5 | Apertus-70B-Instruct-2509 | 31.94 |
| 6 | Mistral Small 3.2 | 31.88 |
| 7 | Qwen 2.5 72B Instruct | 31.66 |
| 8 | Gemma 3n E4B (IT) | 31.5 |
| 9 | GPT-4.1 | 31.32 |
| 10 | Qwen 3 30B A3B 2507 Instruct | 31.21 |
| 11 | Gemma 4 31B (IT) | 31 |
| 12 | Gemma 3 4B (IT) | 30.76 |
| 13 | Qwen 3 4B 2507 (Thinking) | 30.49 |
| 14 | Llama 3.1 8B Instruct | 30.47 |
| 15 | Gemini 3 Pro (Preview) | 30.46 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-estonian-summarization-err-news · How It Works · Data refreshed daily, snapshot 2026-09-05.