EuroEval Greek NLU: leaderboard
Greek-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: NLU Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 208 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) (Thinking) | 72.39 | #82 (Gemini 3 Flash (Preview)) |
| 2 | Gemma 4 31B (IT) | 71.68 | #176 |
| 3 | Gemini 3 Flash (Preview) (Non-reasoning) | 71.45 | #82 (Gemini 3 Flash (Preview)) |
| 4 | Llama 3.1 70B | 71.16 | #592 |
| 5 | Claude Sonnet 4.6 | 70.99 | #90 |
| 6 | gemma-3-27B-pt | 69.99 | #502 |
| 7 | GPT-5.4 Mini (2026-03-17) (High) | 69.93 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 8 | Gemini 3 Pro (Preview) | 68.56 | #66 |
| 9 | GPT-5.2 | 68.41 | #110 |
| 10 | Claude Sonnet 4.5 (Thinking) | 68.36 | #142 (Claude Sonnet 4.5) |
| 11 | Grok 4.1 Fast (Reasoning) | 68.23 | #217 (Grok 4.1 Fast) |
| 12 | Gemma 4 26B A4B (IT) | 68.01 | #297 |
| 13 | Gemma 3 27B (IT) | 67.75 | #523 |
| 14 | Gemini 2.5 Flash (Non-reasoning) | 67.21 | #245 (Gemini 2.5 Flash) |
| 15 | Gemini 3.1 Flash Lite (Preview) | 67.06 | #194 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-greek-nlu · How It Works · Data refreshed daily, snapshot 2026-10-20.