EuroEval Polish NLU - ScaLA PL: leaderboard
The "ScaLA PL" subtask of EuroEval Polish NLU. Polish-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. 234 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 71.7 | #66 |
| 2 | Gemini 3 Flash (Preview) (Non-reasoning) | 69.86 | #82 (Gemini 3 Flash (Preview)) |
| 3 | Gemini 3.1 Flash Lite (Preview) | 67.21 | #194 |
| 4 | Gemini 2.5 Flash (Thinking) | 65.39 | #245 (Gemini 2.5 Flash) |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 64.89 | #82 (Gemini 3 Flash (Preview)) |
| 6 | Claude Sonnet 4.6 | 61.86 | #90 |
| 7 | GPT-5.2 | 61.36 | #110 |
| 8 | GPT-5.4 Mini (2026-03-17) (High) | 60.74 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 9 | GPT-5 | 59.8 | #98 |
| 10 | Gemma 4 31B (IT) | 59.77 | #176 |
| 11 | Gemini 2.5 Pro | 59.32 | #152 |
| 12 | Claude Sonnet 4.5 (Thinking) | 56.9 | #142 (Claude Sonnet 4.5) |
| 13 | Gemini 2.5 Flash Lite (Thinking) | 56.05 | #422 (Gemini 2.5 Flash Lite) |
| 14 | GPT-5.4 Nano (2026-03-17) (High) | 55.49 | #266 (GPT-5.4 Nano (2026-03-17)) |
| 15 | EuroLLM-22B-Instruct-2512 | 55.16 | #701 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-polish-nlu-scala-pl · How It Works · Data refreshed daily, snapshot 2026-10-20.