Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.58Mean@32
30
Apr 30, 2026
83.8Acc
30
Feb 26, 2026
75.8Accuracy
30
Feb 26, 2026
0.93Accuracy
30
Feb 26, 2026
100Top-1 Accuracy (Maj@1)
30
Feb 26, 2026
88Accuracy
30
Feb 26, 2026
75.9Accuracy
30
Mar 4, 2026
20Pass@1 Accuracy
29
Jun 30, 2026
26.7Pass@1 Score
29
Jun 30, 2026
75.2Accuracy (%)
29
Jun 1, 2026
76.36Average Score
29
Jun 2, 2026
40Pass@1
29
Jun 2, 2026
82.7Pass@1
29
May 20, 2026
59.1Average Success Rate (avg@32)
29
May 14, 2026
72.2Pass@1
29
May 18, 2026
86.67Accuracy
29
Apr 2, 2026
12.7Latency (s)
29
Apr 2, 2026
17.07Latency (s)
29
Apr 2, 2026
29.58Latency (s)
29
Apr 2, 2026
32.93Latency (s)
29
Apr 2, 2026
26,854.97Input Tokens
29
Apr 2, 2026
29,494.1Input Tokens
29
Apr 2, 2026
25,573.15Input Tokens
29
Apr 2, 2026
32,881.13Input Tokens
29
Apr 2, 2026
77.13Accuracy
29
Jun 16, 2026