EuroEval Slovak NLU - ScaLA SK: leaderboard
The "ScaLA SK" subtask of EuroEval Slovak NLU. Slovak-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 Pro (Preview) | 69 | #66 |
| 2 | Gemini 3.1 Flash Lite (Preview) | 66.71 | #194 |
| 3 | Gemini 2.5 Flash (Thinking) | 65.44 | #245 (Gemini 2.5 Flash) |
| 4 | Gemini 2.5 Pro | 64.97 | #152 |
| 5 | Gemini 3 Flash (Preview) (Thinking) | 64.02 | #82 (Gemini 3 Flash (Preview)) |
| 6 | GPT-5 | 63.79 | #98 |
| 7 | Gemini 3 Flash (Preview) (Non-reasoning) | 63.09 | #82 (Gemini 3 Flash (Preview)) |
| 8 | Claude Sonnet 4.6 | 61.8 | #90 |
| 9 | Gemma 4 31B (IT) | 61.46 | #176 |
| 10 | GPT-5.4 Mini (2026-03-17) (High) | 61.45 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 11 | Claude Sonnet 4.5 (Thinking) | 60.17 | #142 (Claude Sonnet 4.5) |
| 12 | Gemini 2.5 Flash Lite (Thinking) | 58.55 | #422 (Gemini 2.5 Flash Lite) |
| 13 | GPT-5 Mini (2025-08-07) | 58.36 | #172 |
| 14 | Qwen 3 32B (Non-reasoning) | 56.94 | #443 (Qwen 3 32B) |
| 15 | Qwen 3.5 35B A3B Base | 56.67 | #310 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-slovak-nlu-scala-sk · How It Works · Data refreshed daily, snapshot 2026-10-20.