Medical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
58.3Accuracy
4
Jun 11, 2026
41.67Accuracy
4
Jun 11, 2026
31.26Accuracy
4
Jun 11, 2026
35.1Accuracy (Before)
4
May 26, 2026
55.6Accuracy
4
May 26, 2026
40.91Pass Rate
4
Apr 14, 2026
86.23Accuracy
4
Mar 18, 2026
36.91Pass@1
4
Feb 26, 2026
50.7Accuracy
3
May 26, 2026
64.7Accuracy
3
May 26, 2026
76Accuracy
3
May 26, 2026
78.1Accuracy
3
May 26, 2026
43.8Accuracy
3
May 26, 2026
59.3Accuracy
3
May 26, 2026
43.7Accuracy
3
Feb 27, 2026
3.8Correctness
2
Jun 30, 2026
0.04Cost (cents)
2
Jun 26, 2026
59.05Accuracy
2
Feb 26, 2026
71.5Accuracy
2
Feb 26, 2026
80.33Accuracy
2
Feb 26, 2026
85.63Accuracy
2
Feb 26, 2026
0.968Accuracy
2
Feb 26, 2026
0Failure Rate
1
Feb 26, 2026