Theorem Proving
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62.5Average Proof Length
9
Apr 30, 2026
57Solved Tests (Correct)
8
May 25, 2026
102Correct Solved Tests Count
8
May 25, 2026
27Solved Tests (Correct)
8
May 25, 2026
5Solved Tests (Correct Entries)
8
May 25, 2026
16pass@32
8
May 7, 2026
631Problem A1 Score
8
Feb 26, 2026
33VR
8
Feb 26, 2026
54False Rate
8
Feb 26, 2026
94FR (Fetch Rate)
8
Feb 26, 2026
91Success Rate
8
Feb 26, 2026
99Success Rate
8
Feb 26, 2026
99Success Rate
8
Feb 26, 2026
25.3Accuracy
7
Feb 26, 2026
41.5Pass Rate
6
Jun 16, 2026
95Solved Rate
6
Apr 30, 2026
8Solved Rate
6
Apr 30, 2026
9Solved Rate
6
Apr 30, 2026
17Solved Count
6
Apr 30, 2026
10Solved Count
6
Apr 30, 2026
10Solved Count
6
Apr 30, 2026
57Success Rate
5
Feb 26, 2026
32.1Pass@64
3
Feb 26, 2026
48.6Pass@1
2
Feb 26, 2026
65.6Pass@8
2
Feb 26, 2026