Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
99.4Pass@1
45
Jun 16, 2026
58.8Accuracy
45
Mar 18, 2026
93.71Accuracy
45
Jul 9, 2026
68.28Accuracy
45
Jun 9, 2026
30.4Accuracy
45
Jun 8, 2026
51.9Pass@1
44
May 22, 2026
70.5Pass@1
44
Apr 15, 2026
85.3Average Pass@32
44
May 14, 2026
90.22Exact Match
44
Apr 20, 2026
82.4Accuracy
44
May 27, 2026
95.7Accuracy (avg@4)
44
May 18, 2026
52Accuracy
44
May 26, 2026
90Pass@1
44
Apr 6, 2026
71.8Pass@1
44
Apr 15, 2026
95.2Accuracy
44
Feb 26, 2026
97.5Accuracy
43
Jun 23, 2026
79.8Overall Score
43
Jun 4, 2026
95.2Accuracy
43
Apr 21, 2026
92Accuracy
43
Jun 29, 2026
73.9Score
43
Jul 7, 2026
83Pass@1
43
Jun 12, 2026
92.3Accuracy (GSM8K)
43
Mar 9, 2026
88.9Accuracy (All)
43
Mar 25, 2026
40.9Avg@16
43
Mar 4, 2026
92.5Pass@1
43
Feb 26, 2026