EuroEval Czech Summarization - Czech News: leaderboard
EuroEval's Czech summarization task on the Czech News dataset — models write abstractive summaries of Czech news articles, scored with automatic text-overlap metrics, from the EuroEval European language model benchmark suite.
Metric: chrF3++ (%). Source: euroeval.com. Saturation forecast: Around 2036. 153 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) (Non-reasoning) | 30.2 | #82 (Gemini 3 Flash (Preview)) |
| 2 | GPT-4.1 | 30.09 | #248 |
| 3 | Apertus-70B-Instruct-2509 | 29.9 | #822 |
| 4 | Gemini 3 Pro (Preview) | 29.82 | #65 |
| 5 | EuroLLM-9B-Instruct | 29.74 | #1054 |
| 6 | Bielik-11B-v2.3-Instruct | 29.54 | #693 |
| 7 | Qwen 3.5 27B FP8 | 29.45 | #162 |
| 8 | Gemini 3 Flash (Preview) (Thinking) | 29.42 | #82 (Gemini 3 Flash (Preview)) |
| 9 | Gemma 3 27B (IT) | 29.39 | #523 |
| 10 | Gemma 3n E4B (IT) | 29.38 | #748 |
| 11 | Qwen 2.5 72B Instruct | 29.37 | #455 |
| 12 | Claude Sonnet 4.5 (Non-reasoning) | 29.27 | #141 (Claude Sonnet 4.5) |
| 13 | Gemini 2.5 Flash Lite (Non-reasoning) | 29.26 | #422 (Gemini 2.5 Flash Lite) |
| 14 | Mistral Small 3.1 | 29.25 | #611 |
| 15 | Grok 4.20 Beta (0309) (Reasoning) | 29.2 | #203 (Grok 4.20 Beta (0309)) |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-czech-summarization-czech-news · How It Works · Data refreshed daily, snapshot 2026-10-21.