Open PL LLM - PolQA Closed Book (generative, 5-shot): leaderboard
Metric: Levenshtein Similarity (%). Source: huggingface.co. 319 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 405B Instruct FP8 | 85.98 |
| 2 | MSH-v1-Bielik-v2.3-Instruct-MedIT-merge | 85.77 |
| 3 | Mistral Large 2 (Jul) | 85.05 |
| 4 | Mistral Large 2 (Nov) Instruct (2411) | 85.05 |
| 5 | Bielik-11B-v2 | 85.05 |
| 6 | Bielik-11B-v2.3-Instruct | 84.11 |
| 7 | Bielik-11B-v2.2-Instruct | 83.59 |
| 8 | Llama 3.1 70B | 83.49 |
| 9 | Llama 4 Scout Base | 83.39 |
| 10 | Bielik-11B-v2.1-Instruct | 83.28 |
| 11 | Llama 3 70B | 83.07 |
| 12 | Bielik-11B-v2.5-Instruct | 82.97 |
| 13 | Bielik-11B-v2.0-Instruct | 82.45 |
| 14 | Mixtral-8x22B-v0.1 | 81.62 |
| 15 | Llama 3.3 70B Instruct | 80.37 |
Interactive version: theaggregate.ai/benchmark?slug=open-pl-llm-polqa-closed-book-generative-5-shot · How It Works · Data refreshed daily, snapshot 2026-09-19.