Medical Knowledge Performance on Polish Board Certification Examinations (test)
69.2Average Score (%)Meta-Llama-3.1-405B-Instruct-FP8
Evaluation Results
| Method | Links | |
|---|---|---|
| Meta-Llama-3.1-405B-Instruct-FP8Parameters (B)=405, Setting=5-shot2025.12 | 69.2 | |
| Mistral-Large-Instruct-2407Parameters (B)=123, Setting=5-shot2025.12 | 64.28 | |
| Qwen2.5-72B-InstructParameters (B)=72.7, Setting=5-shot2025.12 | 63.89 | |
| Meta-Llama-3.1-70B-InstructParameters (B)=70.6, Setting=5-shot2025.12 | 61.75 | |
| Qwen2-72B-InstructParameters (B)=72.7, Setting=5-shot2025.12 | 61.35 | |
| Meta-Llama-3-70B-InstructParameters (B)=70.6, Setting=5-shot2025.12 | 57.51 | |
| Qwen2.5-32BParameters (B)=32.8, Setting=5-shot2025.12 | 55.69 | |
| Qwen2.5-32B-InstructParameters (B)=32.8, Setting=5-shot2025.12 | 54.52 | |
| Bielik-11B-v3.0-InstructParameters (B)=11.2, Setting=5-shot2025.12 | 50.21 | |
| Qwen2.5-14B-InstructParameters (B)=14.8, Setting=5-shot2025.12 | 49.6 | |
| Bielik-11B-v3-Base-20250730Parameters (B)=11.2, Setting=5-shot2025.12 | 45.86 | |
| Bielik-11B-v2.6-InstructParameters (B)=11.2, Setting=5-shot2025.12 | 44.88 | |
| Bielik-11B-v2.5-InstructParameters (B)=11.2, Setting=5-shot2025.12 | 44.85 | |
| GLM-4-9b-chatParameters (B)=9, Setting=5-shot2025.12 | 44.54 | |
| Mistral-Small-Instruct-2409Parameters (B)=22.2, Setting=5-shot2025.12 | 43.6 | |
| Bielik-4.5B-v3.0-InstructParameters (B)=4.8, Setting=5-shot2025.12 | 43.55 | |
| Bielik-11B-v2.3-InstructParameters (B)=11.2, Setting=5-shot2025.12 | 43.26 | |
| Bielik-11B-v2.1-InstructParameters (B)=11.2, Setting=5-shot2025.12 | 43.16 | |
| Bielik-11B-v2.2-InstructParameters (B)=11.2, Setting=5-shot2025.12 | 43.05 | |
| Qwen2.5-7B-InstructParameters (B)=7.6, Setting=5-shot2025.12 | 42.69 | |
| Bielik-11B-v2.0-InstructParameters (B)=11.2, Setting=5-shot2025.12 | 41.53 | |
| Meta-Llama-3.1-8B-InstructParameters (B)=8, Setting=5-shot2025.12 | 40.6 | |
| Mistral-Nemo-Instruct-2407Parameters (B)=12.2, Setting=5-shot2025.12 | 40.36 | |
| Bielik-11B-v2Parameters (B)=11.2, Setting=5-shot2025.12 | 39.98 | |
| PLLuM-12B-nc-chat-250715Parameters (B)=12.2, Setting=5-shot2025.12 | 38.53 | |
| PLLuM-12B-chatParameters (B)=12.2, Setting=5-shot2025.12 | 36.51 | |
| EuroLLM-9B-InstructParameters (B)=9, Setting=5-shot2025.12 | 35.96 | |
| Mistral-7B-Instruct-v0.3Parameters (B)=7, Setting=5-shot2025.12 | 31.24 | |
| Bielik-7B-Instruct-v0.1Parameters (B)=7.2, Setting=5-shot2025.12 | 29.74 |