Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.075ECE
17
Mar 5, 2026
10.64ECE
17
Mar 5, 2026
7ECE
17
Mar 5, 2026
7.26ECE
17
Mar 5, 2026
40.8Accuracy (%)
17
Mar 4, 2026
64.2ALL Score
17
Mar 4, 2026
49.63Last Score
17
Apr 8, 2026
87.64Accuracy
17
Apr 14, 2026
95.6Accuracy
17
Mar 4, 2026
5.6Relative Speedup
17
Apr 8, 2026
94.62ACC
17
Jul 1, 2026
675Tokens
17
Feb 26, 2026
452Tokens Used
17
Feb 26, 2026
94.1Avg@4 (%)
17
Feb 26, 2026
0.651Average@2
17
Jun 30, 2026
78.8Score
17
Feb 26, 2026
3.3Accuracy (G8->AM)
17
Feb 26, 2026
57.2Pass@1 Accuracy (@16)
17
Feb 26, 2026
91.8Pass@1 (Avg @16)
17
Feb 26, 2026
51.3Pass@1 (Avg@16)
17
Feb 26, 2026
99.6Accuracy (Avg@8)
17
Feb 26, 2026
73.3Accuracy (Pass@1)
17
Feb 26, 2026
72.9Accuracy (Avg@8)
17
Feb 26, 2026
96Accuracy (Pass@1)
17
Feb 26, 2026
74.3Accuracy
17
Feb 26, 2026