Theorem Proving
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
63.9Success Rate
59
Feb 26, 2026
87.9Pass@32
29
May 7, 2026
21.5Pass Rate (%)
27
Jun 19, 2026
52Pass@64
24
Feb 26, 2026
668Solved Rate
23
Mar 12, 2026
70.8Pass@32
19
Mar 24, 2026
46.7Pass@32
16
Mar 24, 2026
53.21Pass@1
16
Feb 26, 2026
600Proofs Found (Test)
14
Feb 26, 2026
72Accuracy
13
May 25, 2026
8Proof Length
13
Apr 30, 2026
5.5Proof Length
13
Apr 30, 2026
17Proof Length
13
Apr 30, 2026
27Solved Problems
13
Apr 30, 2026
25Solved Problems
13
Apr 30, 2026
19Solved Problems
13
Apr 30, 2026
17Solved Problems
13
Apr 30, 2026
36Solved Problems
13
Apr 30, 2026
57Solved Problems
13
Apr 30, 2026
13.5Accuracy
13
Feb 26, 2026
668Solved Count
12
Jul 1, 2026
34Success Rate
12
May 7, 2026
41.11Pass@1
12
Feb 26, 2026
25.4Accuracy
11
Feb 26, 2026
60.2Cumulative Pass Rate
10
Feb 26, 2026