Open PL LLM - RAG — leaderboard
Metric: Average RAG Score (%). Source: huggingface.co. 287 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Bielik-11B-v2.2-Instruct | 76.92 |
| 2 | Bielik-11B-v2.1-Instruct | 76.79 |
| 3 | Bielik-11B-v2.3-Instruct | 76.2 |
| 4 | Mistral Large 2 (Jul) | 75.78 |
| 5 | MSH-v1-Bielik-v2.3-Instruct-MedIT-merge | 75.62 |
| 6 | Bielik-11B-v2.0-Instruct | 75.5 |
| 7 | Qwen 2 72B | 75.48 |
| 8 | Mistral Large 2 (Nov) Instruct (2411) | 74.96 |
| 9 | Llama 3.3 70B Instruct | 74.62 |
| 10 | Llama 3.1 405B Instruct FP8 | 74.34 |
| 11 | Gemma 3 27B (IT) | 73.92 |
| 12 | Llama 4 Scout Instruct | 73.89 |
| 13 | QwQ 32B-Preview | 73.8 |
| 14 | Qwen 3 14B | 73.73 |
| 15 | Llama 3.1 70B Instruct | 73.67 |
Interactive version: theaggregate.ai/benchmark?slug=open-pl-llm-rag · How the rankings work · Data refreshed daily, snapshot 2026-07-22.