Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Autoformalization and Proving on CombiBench (N=100)
Loading...
96
Pass@64
Ground truth statement (oracle)
37.76
52.88
68
83.12
Mar 20, 2026
Pass@64
Complete@64
Theorem Complete@64
Updated 27d ago
Evaluation Results
Method
Method
Links
Pass@64
Complete@64
Theorem Complete@64
Ground truth statement (oracle)
2026.03
96
68
18
FormalEvolve
K=2
2026.03
44
27
13
Sample
2026.03
41
23
8
Compile+Semantic Repair
Source=Kimina
2026.03
40
23
8
Feedback
Search any
task
Search any
task