MATH
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MATH
81.7AUROC
18
MATH
70.25Pass@1
18
MATH 500
96.4Accuracy
18
MATH
97.3Accuracy (mv %)
18
MATH 500
89.7Accuracy
18
MATH 500
81.2Accuracy
18
MATH500
79.3Avg Score (@8)
18
MATH-500
85Avg@4 Accuracy
18
MATH
78.3Pass@1 Accuracy
18
MATH 500
89.8Accuracy
18
MATH
93.2ACC (maj@8)
18
MATH500
89.58Accuracy (MATH500)
18
Math
72.1Accuracy
18
MATH
89.1Accuracy (Knowledge Gap)
18
MATH500
68.6Pass@1
18
Math500
3,636.1Throughput
18
Math
0.532AUC
18
Math Category Average (test)
51.5Accuracy
18
MATH-500 (in-distribution)
62.4Pass@1 Accuracy
18
MATH500
66.4Pass@1
18
MATH 500
1Speed
18
MATH
0.027Brier Score
18
MATH 500
94.1Accuracy
18
MATH
86.58Pass@1
18
Math MATH500, AIME24, Minerva-Math, AMC23
90.6MATH500 Score
18