Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

EuroEval Czech Summarization - Czech News — leaderboard

Metric: Score (%). Source: euroeval.com. 153 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview) (Non-reasoning)30.2
2GPT-4.130.09
3Apertus-70B-Instruct-250929.9
4Gemini 3 Pro (Preview)29.82
5Bielik-11B-v2.3-Instruct29.54
6Gemma 3 27B (IT)29.39
7Gemma 3n E4B (IT)29.38
8Qwen 2.5 72B Instruct29.37
9Claude Sonnet 4.5 (Non-reasoning)29.27
10Gemini 2.5 Flash Lite (Non-reasoning)29.26
11Mistral Small 3.129.25
12Grok 4.20 Beta (0309) (Reasoning)29.2
13Ministral-3-8B-Instruct-251229.19
14Qwen 3 30B A3B 2507 Instruct29.17
15Gemini 3.1 Flash Lite (Preview)29.17

Interactive version: theaggregate.ai/benchmark?slug=euroeval-czech-summarization-czech-news · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.