EuroEval Slovak NLU - ScaLA SK: leaderboard
Metric: Linguistic acceptability Score (%). Source: euroeval.com. 204 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 69 |
| 2 | Gemini 3.1 Flash Lite (Preview) | 66.71 |
| 3 | Gemini 2.5 Flash (Thinking) | 65.44 |
| 4 | Gemini 2.5 Pro | 64.97 |
| 5 | GPT-5 | 63.79 |
| 6 | GPT-5.4 Mini (Medium) | 62.87 |
| 7 | Claude Sonnet 4.6 | 61.8 |
| 8 | Gemma 4 31B (IT) | 61.46 |
| 9 | GPT-5.4 Mini (High) | 61.45 |
| 10 | GPT-5.4 Nano (Medium) | 60.28 |
| 11 | Claude Sonnet 4.5 (Thinking) | 60.17 |
| 12 | GPT-5 Mini | 58.36 |
| 13 | Gemma 3 27B (IT) | 56.41 |
| 14 | MamayLM-Gemma-3-12B-IT-v1.0 | 54.55 |
| 15 | GPT-5.2 | 53.84 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-slovak-nlu-scala-sk · How It Works · Data refreshed daily, snapshot 2026-09-05.