Policy improvement
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
6.5Patient 596 Result
9
Feb 26, 2026
38Success Rate
4
Jul 9, 2026
17Rate
4
Jul 9, 2026
19Rate
2
Jul 9, 2026
92Success Rate
2
Jul 9, 2026
61Improvement Rate
2
Jul 9, 2026
0Improvement Rate
2
Jul 9, 2026
53Performance Rate
2
Jul 9, 2026