EuroEval Hungarian NLU - Szeged NER: leaderboard
The "Szeged NER" subtask of EuroEval Hungarian NLU. Hungarian-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Micro F1 excluding MISC (%). Source: euroeval.com. Saturation forecast: Around January 2027. 203 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.3 70B Instruct | 79.97 | #534 |
| 2 | Qwen 3 4B 2507 (Thinking) | 79.07 | #538 (Qwen 3 4B 2507) |
| 3 | Gemma 4 31B (IT) | 76.62 | #176 |
| 4 | Voxtral-Small-24B-2507 | 75.31 | #581 |
| 5 | GPT-5.4 Mini (2026-03-17) (High) | 74.83 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 6 | Llama 3.1 70B | 74.46 | #592 |
| 7 | Mistral Small 3.1 | 74.03 | #610 |
| 8 | GPT-OSS-20B (Low) | 73.76 | #518 (GPT-OSS-20B) |
| 9 | Mistral Small 3.2 | 73.26 | #605 |
| 10 | GPT-5 | 73.13 | #98 |
| 11 | GPT-5 Nano | 72.84 | #425 |
| 12 | Gemma 4 26B A4B (IT) | 72.33 | #297 |
| 13 | Claude Sonnet 4.5 (Thinking) | 72.24 | #142 (Claude Sonnet 4.5) |
| 14 | cogito-v1-preview-qwen-14B | 72.19 | |
| 15 | NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 72.03 | #679 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-hungarian-nlu-szeged-ner · How It Works · Data refreshed daily, snapshot 2026-10-20.