Mathematics
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
22.54Accuracy
9
Jun 2, 2026
67.7Accuracy
9
May 15, 2026
80Accuracy
9
May 15, 2026
97.36Exact Match (EM)
9
Mar 20, 2026
66.56Avg@10
9
Feb 26, 2026
5.139Mean Borda Score
8
Apr 15, 2026
61.9Pass@1
8
Mar 4, 2026
89.5Score
8
Feb 26, 2026
77.29Accuracy
6
Jun 30, 2026
56.7Accuracy
6
Jun 23, 2026
70Accuracy
6
Jun 23, 2026
48.1Accuracy
6
Apr 21, 2026
16.83Throughput (Req/s)
6
Apr 10, 2026
39.43Req/s
6
Apr 10, 2026
40.31Accuracy
6
Apr 7, 2026
47.1Accuracy
6
Feb 26, 2026
3.6ECE
5
May 25, 2026
49.46Accuracy
5
Apr 30, 2026
0.792Score (%)
5
Feb 26, 2026
0.76CBRC Score
5
Feb 26, 2026
78.8Pass@1
5
Feb 26, 2026
90Pass@1
4
Jul 7, 2026
83.3Accuracy
4
Jun 9, 2026
15.9Pass@1
4
May 29, 2026
29.6Pass@1
4
May 29, 2026