Step-wise Verification
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
62.3Macro F1
18
Feb 27, 2026
63.9Macro F1
18
Feb 27, 2026
66.7Macro F1
18
Feb 27, 2026
62.8Macro F1
18
Feb 27, 2026
61.7Macro F1
18
Feb 27, 2026
59.2Macro F1
18
Feb 27, 2026
37.3TNR
15
May 21, 2026
72.3F1 Score
13
May 21, 2026
63.1TNR
13
May 21, 2026
61.3TNR
13
May 21, 2026
69.5TNR
13
May 21, 2026
68.6True Negative Rate
13
May 21, 2026