EuroEval Greek NLU: leaderboard
Metric: NLU Average Score (%). Source: euroeval.com. 208 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemma 4 31B (IT) | 71.68 |
| 2 | Llama 3.1 70B | 71.16 |
| 3 | Claude Sonnet 4.6 | 70.99 |
| 4 | gemma-3-27B-pt | 69.99 |
| 5 | GPT-5.4 Mini (High) | 69.93 |
| 6 | Gemini 3 Pro (Preview) | 68.56 |
| 7 | GPT-5.2 | 68.41 |
| 8 | Claude Sonnet 4.5 (Thinking) | 68.36 |
| 9 | Grok 4.1 Fast (Reasoning) | 68.23 |
| 10 | Gemma 4 26B A4B (IT) | 68.01 |
| 11 | Gemma 3 27B (IT) | 67.75 |
| 12 | GPT-5.4 Mini (Medium) | 67.16 |
| 13 | Gemini 3.1 Flash Lite (Preview) | 67.06 |
| 14 | GPT-5 | 66.59 |
| 15 | Mistral Small 3.2 | 66.18 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-greek-nlu · How It Works · Data refreshed daily, snapshot 2026-09-05.