EuroEval Greek NLU - ScaLA EL: leaderboard

Metric: Linguistic acceptability Score (%). Source: euroeval.com. 204 models tracked.

Top models

#ModelScore
1Gemma 4 31B (IT)62.04
2GPT-5.4 Mini (High)57.93
3GPT-4.157.62
4Claude Sonnet 4.657.37
5GPT-5.256.23
6Grok 4.1 Fast (Reasoning)54.88
7Qwen 3.5 9B54.65
8gemma-3-27B-pt54.48
9Gemini 3 Pro (Preview)54.39
10Gemma 3 27B (IT)54.3
11Gemini 2.5 Pro53.31
12Llama 3.1 70B53.21
13Gemma 4 26B A4B (IT)53.11
14GPT-551.07
15Gemini 3.1 Flash Lite (Preview)50.91

Interactive version: theaggregate.ai/benchmark?slug=euroeval-greek-nlu-scala-el · How It Works · Data refreshed daily, snapshot 2026-09-05.