Math Word Problems
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98.68Accuracy
35
Jun 19, 2026
91.4Accuracy
18
Jun 19, 2026
89.2Expected Utility
10
May 14, 2026
83R Score
10
Mar 23, 2026
53Comparable SC Rate
8
Feb 27, 2026
93.64Accuracy (Source Lib.)
5
Jun 19, 2026