Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Medical Question Answering on MedQA (MAE)
Loading...
0.038
MAE
Ensemble
0.02272
0.12586
0.229
0.33214
May 8, 2026
MAE
Updated 23d ago
Evaluation Results
Method
Method
Links
MAE
Ensemble
Num. queries=64, Evalu...
2026.05
0.038
DKPS
Num. queries=64, Evalu...
2026.05
0.039
Sample Score
Num. queries=64, Evalu...
2026.05
0.044
Ensemble
Num. queries=16, Evalu...
2026.05
0.065
DKPS
Num. queries=16, Evalu...
2026.05
0.066
Sample Score
Num. queries=16, Evalu...
2026.05
0.093
DKPS
Num. queries=4, Evalua...
2026.05
0.094
Ensemble
Num. queries=4, Evalua...
2026.05
0.094
DKPS
Num. queries=1, Evalua...
2026.05
0.121
Ensemble
Num. queries=1, Evalua...
2026.05
0.121
Pop. Mean
Num. queries=1, Evalua...
2026.05
0.131
Pop. Mean
Num. queries=4, Evalua...
2026.05
0.131
Pop. Mean
Num. queries=16, Evalu...
2026.05
0.131
Pop. Mean
Num. queries=64, Evalu...
2026.05
0.131
Sample Score
Num. queries=4, Evalua...
2026.05
0.189
Sample Score
Num. queries=1, Evalua...
2026.05
0.42
Feedback
Search any
task
Search any
task