MATH
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
MATH 500
0.95Sel-AUC
45
MATH 4-shot
42.6Accuracy
45
MATH 500
95Accuracy
45
MATH (test)
93.22Accuracy
45
MATH
82.4Accuracy
44
MATH 500
95.7Accuracy (avg@4)
44
MATH
79.8Overall Score
43
Math-500
95.2Accuracy
43
GSM8K MATH-500 (test)
92.3Accuracy (GSM8K)
43
MATH
0.913AUROC
43
MATH-OAI
73.83Avg@16
42
MATH 500
95.2Pass@1
42
MATH-500 (test)
80.2Score (%)
41
Math
78.6Math500 Score
41
MATH 500
88.89AUROC
41
MATH500
96.2Accuracy
41
MATH
52.3Accuracy
41
Math
88.6M-F1
40
MATH
88.4Accuracy
40
MATH 500
93.16Accuracy
40
MATH500
91.3Pass@1
40
MATH
95.7Accuracy
40
MATH 500
96.5Acc
40
MATH
3.94Average Time
39
MATH 500
96.8Pass@4
39