Reasoning Quality Assessment
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
77.94AUROC
34
Mar 12, 2026
0.873AUROC
32
Mar 12, 2026
80.61AUROC
32
Mar 12, 2026
0.83AUROC
32
Mar 12, 2026
0.719AUROC
32
Mar 12, 2026
4.6Recursion Depth
2
Mar 26, 2026