EuroEval Slovak NLU: leaderboard
Slovak-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: Around April 2027. 208 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B (IT) | 63.33 | #176 |
| 2 | Mistral Small 3.2 | 62.65 | #605 |
| 3 | Gemini 3 Pro (Preview) | 62.58 | #66 |
| 4 | Voxtral-Small-24B-2507 | 62.09 | #581 |
| 5 | Mistral Small 3.1 | 61.73 | #610 |
| 6 | Magistral Small 1.2 | 61.56 | #570 |
| 7 | GPT-5 | 60.18 | #98 |
| 8 | Qwen 2.5 72B Instruct | 59.91 | #454 |
| 9 | GPT-5.4 Mini (2026-03-17) (High) | 59.72 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 10 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 59.72 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 11 | Claude Sonnet 4.5 (Thinking) | 59.7 | #142 (Claude Sonnet 4.5) |
| 12 | Gemini 2.5 Flash (Thinking) | 59.62 | #245 (Gemini 2.5 Flash) |
| 13 | Gemini 3.1 Flash Lite (Preview) | 59.29 | #194 |
| 14 | Gemini 3 Flash (Preview) (Non-reasoning) | 59.28 | #82 (Gemini 3 Flash (Preview)) |
| 15 | Qwen 3 14B (Non-reasoning) | 59.27 | #537 (Qwen 3 14B) |
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 · How It Works · Data refreshed daily, snapshot 2026-10-20.