Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Formal Proof Generation on Lean 4 (val)
Loading...
49.8
Pass@1
Ours
8.2
19
29.8
40.6
Mar 19, 2026
Pass@1
Pass@4
Pass@9
Updated 27d ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@4
Pass@9
Ours
Model type=Fine-tuned
2026.03
49.8
52.7
54.1
Leanabell
2026.03
25.4
36
39.9
STP
2026.03
23.7
33.2
37.5
Deepseek-v2
2026.03
14.1
30
36.2
Goedel-v2
2026.03
14
31.1
38.2
Kimina-distill
2026.03
9.8
25.3
35.8
Feedback
Search any
task
Search any
task