EuroEval Slovak NLU - UNER SK — leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 204 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 4B 2507 (Thinking) | 73.36 |
| 2 | Gemma 4 31B (IT) | 72.84 |
| 3 | GPT-5.4 Mini (High) | 67.46 |
| 4 | Llama 3.1 70B | 66.78 |
| 5 | Mistral Small 3.2 | 65.96 |
| 6 | Mistral Small 3.1 | 65.77 |
| 7 | GPT-OSS-20B (Medium) | 65.77 |
| 8 | Gemma 4 26B A4B (IT) | 65.53 |
| 9 | Claude Sonnet 4.5 (Non-reasoning) | 64.49 |
| 10 | Gemini 3 Flash (Preview) (Non-reasoning) | 64.41 |
| 11 | Gemini 2.5 Flash (Non-reasoning) | 64.02 |
| 12 | Claude Sonnet 4.5 (Thinking) | 63.92 |
| 13 | GPT-5 | 63.83 |
| 14 | GPT-5.4 Mini (Medium) | 63.78 |
| 15 | Magistral Small | 63.7 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-slovak-nlu-uner-sk · How the rankings work · Data refreshed daily, snapshot 2026-07-22.