Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Formal Theorem Proving on PutnamBench
Loading...
87.9
Solve Rate
Seed-Prover 1.5
-1.956
21.372
44.7
68.028
Oct 13, 2025
Nov 4, 2025
Nov 27, 2025
Dec 20, 2025
Jan 12, 2026
Feb 4, 2026
Feb 27, 2026
Solve Rate
Solved Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Solve Rate
Solved Count
Seed-Prover 1.5
Compute Budget=10 H20...
2025.12
87.9
580
Seed-Prover 1.5
2026.02
87.9
-
Aleph Prover
Compute Budget=avg 183...
2025.12
75.8
-
Hilbert
Compute Budget=avg pas...
2025.12
70
-
Hilbert
pass@k=pass@1840
2026.02
70
-
AlphaProof
Compute Budget=500 TPU...
2025.12
56.1
-
AxProverBase
underlying LLM=Opus 4....
2026.02
54.7
-
Seed-Prover 1.0 (medium)
Compute Budget=18 H20...
2025.12
50.4
-
GAR DeepSeek-Prover
2025.10
24
-
DeepSeek-Prover-V2-7B
2025.10
22
-
Ax-Prover
pass@k=pass@1
2026.02
13.8
-
Goedel Prover V2
pass@k=pass@184
2026.02
13
-
DeepSeek V2
pass@k=pass@1024
2026.02
7.1
-
Kimina Prover
pass@k=pass@192
2026.02
1.5
-
Feedback
Search any
task
Search any
task