List your company

Medical Question Answering on Medec

69.2AccuracyBFRS
51.41656.03360.6565.267Nov 25, 2025

Evaluation results

MethodLinks
BFRSModel=o3 Mini2025.1169.2
HELM BaselineModel=o3 Mini2025.1168.7
Zero-Shot PredictModel=o3 Mini2025.1168.3
MIPROv2Model=o3 Mini2025.1168.3
Zero-Shot CoTModel=o3 Mini2025.1168.2
HELM BaselineModel=Claude 3.7 Sonnet2025.1162.8
MIPROv2Model=Claude 3.7 Sonnet2025.1162.5
MIPROv2Model=Llama 3.3 70B2025.1162
Zero-Shot CoTModel=Claude 3.7 Sonnet2025.1161.8
MIPROv2Model=Gemini 2.0 Flash2025.1160.8
BFRSModel=Claude 3.7 Sonnet2025.1160.5
Zero-Shot CoTModel=Llama 3.3 70B2025.1160.1
BFRSModel=Llama 3.3 70B2025.1160.1
MIPROv2Model=GPT 4o2025.1159.8
HELM BaselineModel=Gemini 2.0 Flash2025.1159.6
Zero-Shot CoTModel=Gemini 2.0 Flash2025.1159.5
Zero-Shot CoTModel=GPT 4o2025.1159.5
BFRSModel=GPT 4o2025.1159.5
Zero-Shot PredictModel=Gemini 2.0 Flash2025.1159.3
BFRSModel=Gemini 2.0 Flash2025.1159.1
Zero-Shot PredictModel=Claude 3.7 Sonnet2025.1158.3
HELM BaselineModel=GPT 4o2025.1158
Zero-Shot PredictModel=GPT 4o2025.1157.3
MIPROv2Model=Qwen3 4B2025.1156.6
BFRSModel=Qwen3 4B2025.1156.4
Zero-Shot PredictModel=Llama 3.3 70B2025.1153.6
Zero-Shot CoTModel=Qwen3 4B2025.1153.6
HELM BaselineModel=Llama 3.3 70B2025.1152.9
Zero-Shot PredictModel=Qwen3 4B2025.1152.3
HELM BaselineModel=Qwen3 4B2025.1152.1