Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
1.398HV Value
6
Feb 26, 2026
61.5Accuracy
6
Feb 26, 2026
88.59Score
6
Feb 26, 2026
76.16Accuracy
6
Feb 26, 2026
40.4Average Diffusion Steps
6
Feb 26, 2026
86.47Task 1 Accuracy
6
Feb 26, 2026
10.82Error Rate (%)
6
Feb 26, 2026
4.01Error Rate (%)
6
Feb 26, 2026
2.57Error Rate
6
Feb 26, 2026
82.1Accuracy
5
Jul 7, 2026
94.8Score
5
Jun 23, 2026
50.94Score
5
Jun 16, 2026
81.93Score
5
Jun 16, 2026
52.37Score
5
Jun 16, 2026
69.85Accuracy
5
May 26, 2026
83.68PIQA Accuracy
5
May 25, 2026
44.1Accuracy
5
May 20, 2026
60Accuracy (HLE Verified Gold)
5
May 15, 2026
50.7Accuracy
5
May 13, 2026
41.6Accuracy
5
May 11, 2026
66GPQA Accuracy
5
May 11, 2026
56.52Accuracy
5
Apr 30, 2026
87.48avg.@8 Score
5
Apr 23, 2026
93.2Accuracy
5
Apr 13, 2026
10.62Avg Length
5
Mar 16, 2026