Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
50Accuracy
52
Feb 26, 2026
87.6Accuracy
52
May 12, 2026
32.63Pass@1 Accuracy
51
Jun 30, 2026
57.4Accuracy
51
Apr 20, 2026
67.5Accuracy
51
Jun 5, 2026
86.13Score
51
Jun 26, 2026
80Accuracy
51
Feb 26, 2026
78.2SVAMP
51
Jun 2, 2026
83.3Accuracy
51
Apr 16, 2026
95.3Pass@1
51
May 22, 2026
36.35Avg@32
50
Jun 23, 2026
45.42Accuracy (HMMT 25)
50
May 27, 2026
94.81Accuracy
50
Apr 14, 2026
69.8Pass@1
50
Feb 26, 2026
68.8Accuracy
50
Mar 18, 2026
96.7Score
50
Feb 26, 2026
97Accuracy
50
Feb 26, 2026
40.2Mean Wall-Clock Time
49
Jun 26, 2026
67.8Accuracy
49
Jun 23, 2026
63Average Accuracy
49
May 27, 2026
89.8Avg@16 Score
48
May 4, 2026
92.6Accuracy
48
Jun 17, 2026
66.51Accuracy
48
Mar 4, 2026
73.59Accuracy
48
Mar 4, 2026
77.6Avg@5 Score
48
Feb 26, 2026