Open PL LLM - KLEJ NER (generative, 5-shot): leaderboard
Named-entity category classification of Polish text fragments from the KLEJ benchmark (NKJP-NER). Open PL LLM Leaderboard (SpeakLeash), 5-shot, generative variant: the answer is extracted from generated text; accuracy (%), higher is better. Runs not available on the Hugging Face Hub are excluded.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Around February 2027. 319 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Mistral Large 2 (Nov) Instruct (2411) | 64.92 | #480 |
| 2 | Llama 3.1 405B Instruct FP8 | 64.09 | #400 |
| 3 | Mistral Large 2 (Jul) | 63.36 | #490 |
| 4 | Qwen 2.5 32B | 61.9 | #544 |
| 5 | Qwen 2.5 7B Instruct | 61.37 | #863 |
| 6 | QwQ 32B-Preview | 61.22 | #671 |
| 7 | Llama 3.3 70B Instruct | 60.88 | #541 |
| 8 | Qwen 3 14B | 60.88 | #542 |
| 9 | Qwen 3 32B | 60.79 | #449 |
| 10 | Qwen 2.5 32B Instruct | 60.79 | #509 |
| 11 | QwQ-32B | 60.5 | #422 |
| 12 | Qwen 2.5 72B | 60.25 | #512 |
| 13 | Llama 3.1 Nemotron 70B Instruct | 59.77 | #563 |
| 14 | WizardLM-2 8x22B | 59.33 | #723 |
| 15 | Llama 3.1 70B Instruct | 59.28 | #567 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-pl-llm-klej-ner-generative-5-shot · How It Works · Data refreshed daily, snapshot 2026-11-05.