EuroEval Greek Summarization - Greek Wikipedia — leaderboard

Metric: Score (%). Source: euroeval.com. 147 models tracked.

Top models

#ModelScore
1Llama 3.1 70B36.77
2Ministral 3 14B34.32
3Gemini 3.1 Flash Lite (Preview)32.85
4Ministral 3 8B32.63
5Gemini 2.5 Flash Lite (Thinking)32.59
6Llama 3.3 70B Instruct32.54
7Claude Haiku 4.5 (20251001)32.52
8GPT-4.132.49
9Ministral-3-14B-Instruct-251232.49
10Ministral-3-8B-Instruct-251232.23
11Claude Sonnet 4.5 (Thinking)32.17
12EuroLLM-22B-Instruct-251232.15
13Gemini 3 Pro (Preview)31.97
14GPT-5 Mini31.77
15GPT-5.231.73

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