Medical Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
58.56Overall Score
4
Mar 24, 2026
100Success Rate (SR)
4
Mar 10, 2026
66.67Accuracy
4
Feb 26, 2026
53ROUGE-1
4
Feb 26, 2026
65.2Pass@1
4
Feb 26, 2026
96.12Pass@1
4
Feb 26, 2026
72.45Pass@1
4
Feb 26, 2026
94.16Pass@1
4
Feb 26, 2026
95.78Pass@1
4
Feb 26, 2026
97.88Pass@1
4
Feb 26, 2026
96.21Pass@1
4
Feb 26, 2026
69.47Pass@1
4
Feb 26, 2026
77.2Pass@1
4
Feb 26, 2026
86Accuracy
4
Feb 26, 2026
91Accuracy
4
Feb 26, 2026
4PROMETHEUS-2 Average Score
3
Jul 3, 2026
56.7Health Score
3
Jun 30, 2026
90.9Score
3
Jun 23, 2026
99Accuracy (Web Search On)
3
Jun 5, 2026
74.7Accuracy
3
Mar 5, 2026
88Accuracy
3
Mar 5, 2026
76.5Accuracy
3
Mar 5, 2026
63.41Char Deletion Robustness
3
Feb 26, 2026
0.83Honesty
3
Feb 26, 2026
86.7Accuracy
3
Feb 26, 2026