EuroEval Czech NLU - PONER: leaderboard
Metric: Named entity recognition Score (%). Source: euroeval.com. 229 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 69.75 |
| 2 | GPT-5.4 Mini (High) | 65.91 |
| 3 | GPT-5 | 65.66 |
| 4 | Grok 4.20 Beta (0309) (Reasoning) | 63.6 |
| 5 | Mistral Small 3.1 | 62.66 |
| 6 | Qwen 3 4B 2507 (Thinking) | 62.54 |
| 7 | GPT-5.4 Mini (Medium) | 62.43 |
| 8 | Mistral Small 3.2 | 62.28 |
| 9 | Magistral Small 1.2 | 60.05 |
| 10 | gemma-3-27B-pt | 59.59 |
| 11 | Llama 3.1 70B | 59.01 |
| 12 | GPT-OSS-20B (Medium) | 58.8 |
| 13 | GPT-5 Nano | 58.52 |
| 14 | Gemini 3.1 Flash Lite (Preview) | 57.99 |
| 15 | Gemini 3 Pro (Preview) | 57.9 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-czech-nlu-poner · How It Works · Data refreshed daily, snapshot 2026-09-05.