List your company

Medical Question Answering on MedXpertQA-R

11.12Pass@1SHIFT
2.00964.37486.749.1052May 27, 2026

Evaluation results

MethodLinks
SHIFTTrain Size=0.2%2026.0511.12
Qwen3-1.7BTrain Size=100%2026.0510.26
SHIFTTrain Size=0.1%2026.059.62
ClusterTrain Size=0.2%2026.059.35
CoT SimilarityTrain Size=0.1%2026.059.19
CoT SimilarityTrain Size=0.2%2026.059.03
Random (avg)Train Size=0.2%2026.057.88
SC-EntropyTrain Size=0.1%2026.057.79
A-PPLTrain Size=0.2%2026.057.47
SC-EntropyTrain Size=0.2%2026.057.25
CoreSetTrain Size=0.2%2026.057.15
ClusterTrain Size=0.1%2026.056.93
Random (avg)Train Size=0.1%2026.056.84
Q-PPLTrain Size=0.2%2026.056.29
CoreSetTrain Size=0.1%2026.056.02
Q-PPLTrain Size=0.1%2026.055.8
A-PPLTrain Size=0.1%2026.054.51
Qwen3-1.7BTrain Size=N/A2026.052.36