Open PL LLM - DYK (generative, 5-shot): leaderboard
Did You Know: deciding whether a candidate answer to a Polish Wikipedia question is correct. Open PL LLM Leaderboard (SpeakLeash), 5-shot, generative variant: the answer is extracted from generated text; binary F1 (%), higher is better. Runs not available on the Hugging Face Hub are excluded.
Metric: Binary F1 (%). Source: huggingface.co. Saturation forecast: Around February 2027. 319 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 72B Instruct | 78.05 | #469 |
| 2 | Mistral Large 2 (Jul) | 75.86 | #490 |
| 3 | Mistral Large 2 (Nov) Instruct (2411) | 74.19 | #480 |
| 4 | Qwen 2.5 32B | 74.15 | #544 |
| 5 | Llama 3.1 405B Instruct FP8 | 73.71 | #400 |
| 6 | QwQ 32B-Preview | 72.2 | #671 |
| 7 | Llama 3.1 Nemotron 70B Instruct | 71.82 | #563 |
| 8 | Bielik-11B-v2.2-Instruct | 71.53 | #669 |
| 9 | Llama 3.3 70B Instruct | 71.46 | #541 |
| 10 | Bielik-11B-v2.1-Instruct | 71.26 | #679 |
| 11 | Qwen 3 32B | 71.07 | #449 |
| 12 | Qwen 2 72B Instruct | 71.07 | #579 |
| 13 | Qwen 2.5 72B | 70.98 | #512 |
| 14 | Llama 3.1 70B Instruct | 70.95 | #567 |
| 15 | Bielik-11B-v2.3-Instruct | 70.35 | #700 |
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-dyk-generative-5-shot · How It Works · Data refreshed daily, snapshot 2026-11-05.