Medical Knowledge on MedQA
92.8AccuracyPROMPTED
Evaluation Results
| Method | Links | |
|---|---|---|
| PROMPTEDPrompting Technique=PROMPTED2023.10 | 92.8 | |
| Output RefinementPrompting Technique=Output Refinement2023.10 | 90.4 | |
| Fine-Tuned GPT-4o + MedBioRAGBackbone=GPT-4o, Fine-tuned=true, RAG=MedBioRAG2025.12 | 89.47 | |
| Zero-Shot CoTPrompting Technique=Zero-Shot Chain-of-Thought2023.10 | 88.8 | |
| Fine-Tuned GPT-4oBackbone=GPT-4o, Fine-tuned=true2025.12 | 87.88 | |
| GPT-4o + MedBioRAGBackbone=GPT-4o, Fine-tuned=false, RAG=MedBioRAG2025.12 | 86.86 | |
| Zero-ShotPrompting Technique=Zero-Shot2023.10 | 86.8 | |
| GPT-4oBackbone=GPT-4o, Fine-tuned=false2025.12 | 81.82 | |
| GPT-4 + MedBioRAGBackbone=GPT-4, Fine-tuned=false, RAG=MedBioRAG2025.12 | 78.79 | |
| GPT-4o-mini + MedBioRAGBackbone=GPT-4o-mini, Fine-tuned=false, RAG=MedBioRAG2025.12 | 70.71 | |
| GPT-4o-miniBackbone=GPT-4o-mini, Fine-tuned=false2025.12 | 67.68 | |
| GPT-4Backbone=GPT-4, Fine-tuned=false2025.12 | 66.67 | |
| Mistral 8x7BParameters=8x7B, Shots=2-shot2024.10 | 62.2 | |
| Llama 3 8BParameters=8B, Shots=2-shot2024.10 | 60.5 | |
| Shakti-LLMParameters=2.5B, Shots=2-shot2024.10 | 60.3 | |
| Phi-3 Mini-4kShots=2-shot2024.10 | 53.8 | |
| GPT-3.5Backbone=GPT-3.5, Fine-tuned=false2025.12 | 51.52 | |
| Mistral 7BParameters=7B, Shots=2-shot2024.10 | 50 | |
| Gemma 7BParameters=7B, Shots=2-shot2024.10 | 49.6 | |
| GPT-3.5 + MedBioRAGBackbone=GPT-3.5, Fine-tuned=false, RAG=MedBioRAG2025.12 | 45.36 |