Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MATH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mathematical ReasoningMATH500 (test)
Accuracy60.9
922
Mathematical ReasoningMATH
Accuracy95.63
882
Mathematical ReasoningMATH 500
Accuracy (Acc)99.1
600
Mathematical ReasoningMATH 500
Accuracy99.1
589
Mathematical ReasoningMATH
Accuracy94.2
535
Mathematical ReasoningMATH 500
Top-1 Accuracy96.4
452
Mathematical ReasoningMATH 500
Accuracy98.4
442
Mathematical ReasoningMATH (test)
Overall Accuracy94.13
433
Mathematical ReasoningMATH
Accuracy96.67
338
Mathematical ReasoningMATH 500
Pass@1 Rate96
274
Mathematical ReasoningMATH 500
pass@197.3
239
Mathematical Problem SolvingMATH
Accuracy97.6
229
Mathematical ReasoningMATH Hard
Accuracy92.8
208
Mathematical ReasoningMATH 500
Accuracy97.75
183
MathematicsMATH
MATH Accuracy95.1
172
Mathematical ReasoningMATH L5
Accuracy0.859
162
Math ReasoningMATH
Accuracy90.54
160
Mathematical ReasoningMATH (test)
Pass@194.8
151
Mathematical reasoningMATH 500
Accuracy (pass@1)94.8
134
Mathematical ReasoningMath500
Accuracy (ACC)88.2
133
Math ReasoningMATH500
Accuracy95.6
127
MathMATH-500
Accuracy99.2
126
Mathematical reasoningMATH500
Accuracy96.23
124
MathematicsMATH 500
Pass@197.3
122
Mathematical ReasoningMATH-500
Accuracy97.6
119
Showing 25 of 1003 rows
...