Mathematical Problem Solving
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
474N
1
Jun 2, 2026
540N
1
Jun 2, 2026
71.98Pass@1
1
May 19, 2026
60Correctness Ratio
1
May 11, 2026
11Correlation
1
May 11, 2026
13Accuracy (Ratio)
1
May 11, 2026
21Correlation Score
1
May 11, 2026
46Winner
1
Mar 31, 2026
34Winner Count
1
Mar 31, 2026
29Winner Score
1
Mar 31, 2026
2.25Speedup
1
Feb 26, 2026
205Autonomous Resolution
1
Feb 26, 2026
98.3Points
1
Feb 26, 2026
73.8Points
1
Feb 26, 2026
—
—Primary metric
0
Apr 23, 2026
—
—Primary metric
0
Feb 26, 2026
—
—Primary metric
0
Feb 26, 2026
—
—Primary metric
0
Feb 26, 2026