EuroEval Greek NLU - ScaLA EL: leaderboard
The "ScaLA EL" subtask of EuroEval Greek NLU. Greek-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Matthews correlation coefficient (%). Source: euroeval.com. Saturation forecast: Around January 2027. 204 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) (Thinking) | 66.99 | #82 (Gemini 3 Flash (Preview)) |
| 2 | Gemini 3 Flash (Preview) (Non-reasoning) | 66.7 | #82 (Gemini 3 Flash (Preview)) |
| 3 | Gemma 4 31B (IT) | 62.04 | #176 |
| 4 | GPT-5.4 Mini (2026-03-17) (High) | 57.93 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 5 | Gemini 2.5 Flash (Non-reasoning) | 57.72 | #245 (Gemini 2.5 Flash) |
| 6 | GPT-4.1 | 57.62 | #248 |
| 7 | Claude Sonnet 4.6 | 57.37 | #90 |
| 8 | EuroLLM-22B-Instruct-2512 | 57.12 | #701 |
| 9 | GPT-5.2 | 56.23 | #110 |
| 10 | Qwen 3.5 35B A3B Base | 55.39 | #310 |
| 11 | Grok 4.1 Fast (Reasoning) | 54.88 | #217 (Grok 4.1 Fast) |
| 12 | Qwen 3.5 9B | 54.65 | #379 |
| 13 | gemma-3-27B-pt | 54.48 | #502 |
| 14 | Gemini 3 Pro (Preview) | 54.39 | #66 |
| 15 | Gemma 3 27B (IT) | 54.3 | #523 |
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-scala-el · How It Works · Data refreshed daily, snapshot 2026-10-20.