Medical Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
68.89Accuracy
11
Apr 23, 2026
0.92Accuracy
11
Feb 26, 2026
76.4Accuracy
10
Jun 8, 2026
98Calibrated Accuracy
10
Jun 2, 2026
79.61Score
10
May 29, 2026
56.36Score
10
May 29, 2026
66.61Accuracy
10
May 26, 2026
71Pass@1
10
Apr 14, 2026
0.843Accuracy
10
Mar 31, 2026
4.06Tau (τ)
10
Mar 11, 2026
4.32Tau (τ)
10
Mar 11, 2026
4.03Kendall's Tau
10
Mar 11, 2026
4.34Kendall's Tau (τ)
10
Mar 11, 2026
58.7Accuracy
10
Jun 26, 2026
50.4History Accuracy
10
Feb 26, 2026
82Accuracy
10
Feb 26, 2026
92.19Accuracy
9
May 15, 2026
57.61Accuracy (MedQA)
9
Apr 28, 2026
83Accuracy
9
Apr 21, 2026
92Accuracy
9
Apr 8, 2026
60Accuracy
9
Mar 23, 2026
91.3Accuracy
9
Feb 26, 2026
43.2Accuracy (ZH)
9
Feb 26, 2026
84.47Chinese Accuracy
9
Feb 26, 2026
92.5GPT-4 Score
9
Feb 26, 2026