Share your thoughts, 1 month free Claude Pro on usSee more

Medical Knowledge on MedQA

92.8Accuracy

PROMPTED

Updated 1mo ago

Evaluation Results

Method	Links
PROMPTED 2023.10		92.8
Output Refinement 2023.10		90.4
Fine-Tuned GPT-4o + MedBioRAG 2025.12		89.47
Zero-Shot CoT 2023.10		88.8
Fine-Tuned GPT-4o 2025.12		87.88
GPT-4o + MedBioRAG 2025.12		86.86
Zero-Shot 2023.10		86.8
GPT-4o 2025.12		81.82
GPT-4 + MedBioRAG 2025.12		78.79
GPT-4o-mini + MedBioRAG 2025.12		70.71
GPT-4o-mini 2025.12		67.68
GPT-4 2025.12		66.67
Mistral 8x7B 2024.10		62.2
Llama 3 8B 2024.10		60.5
Shakti-LLM 2024.10		60.3
Phi-3 Mini-4k 2024.10		53.8
GPT-3.5 2025.12		51.52
Mistral 7B 2024.10		50
Gemma 7B 2024.10		49.6
GPT-3.5 + MedBioRAG 2025.12		45.36