MATH
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MATH 500
0.861AUROC
18
MATH500
62Pass@1 Rate
18
MATH
93.67Accuracy
18
Math-500
93.5Pass@1 Acc
18
MATH500
84.6Accuracy
18
MATH
0.863Score
18
MATH500
91.9SC Accuracy
18
MATH (test)
42.68MATH Score
18
MATH
47.4Accuracy @ t1
18
MATH 18 (test)
39.7m1@t1
18
Math500
88.4Accuracy
17
MATH (test)
94Algebra Accuracy
17
MATH
8.03Average Acceptance Length (τ)
17
MATH-500
57F1 Score
17
MATH
76.07Best-of-N Accuracy
17
MATH
7.26ECE
17
MATH
2,677.2AUTC Score
17
MATH500 (val)
87.64Accuracy
17
MATH-500
95.6Accuracy
17
MATH 500
452Tokens Used
17
MATH500
94.1Avg@4 (%)
17
MATH500
91.8Pass@1 (Avg @16)
17
MATH500
96Accuracy (Pass@1)
17
MATH 500
92.6Accuracy
16
MATH
69.34Accuracy
16