Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
85.2GSM8K
10
Mar 24, 2026
48.88AGIEval Reasoning Accuracy
10
Mar 23, 2026
86.22Accuracy
10
Mar 23, 2026
78.44Accuracy
10
Mar 23, 2026
82.7What Happened Score
10
Feb 26, 2026
0.634Causal Score
10
Feb 26, 2026
72.19Accuracy
10
Feb 26, 2026
90.8Score
10
Feb 26, 2026
69.44Score
10
Feb 26, 2026
72.75Score
10
Feb 26, 2026
97.88PrOntoQA Score
10
Feb 26, 2026
87.52Overall Score
10
Feb 26, 2026
37.8Score
10
Feb 26, 2026
37.5Score
10
Jul 7, 2026
0.354Accuracy
10
Feb 26, 2026
98.7Accuracy
10
Feb 27, 2026
56Accuracy
10
Feb 27, 2026
26.6Token F1
9
Jun 18, 2026
86.5Accuracy
9
Jun 18, 2026
99.17Avg@64
9
Jun 16, 2026
88.59Score
9
Jun 16, 2026
95.9Accuracy
9
Jun 2, 2026
99.4Accuracy (ARC-E)
9
Jun 2, 2026
15.1Score
9
May 13, 2026
0.151Score
9
May 13, 2026