Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Formal Theorem Proving on ProofNet (test)
Loading...
25.8
Accuracy
DeepSeek-Prover-V1.5-SFT + RMaxTS
15.192
17.946
20.7
23.454
Aug 15, 2024
Accuracy
Pass@1
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Pass@1
DeepSeek-Prover-V1.5-SFT + RMaxTS
Sample budget=4 x 6400
2024.08
25.8
-
DeepSeek-Prover-V1.5-RL + RMaxTS
Sample budget=4 x 6400
2024.08
25.3
-
DeepSeek-Prover-V1.5-SFT
Sample budget=4 x 6400
2024.08
23.7
-
DeepSeek-Prover-V1.5-RL
Sample budget=4 x 6400
2024.08
23.7
-
DeepSeek-Prover-V1.5-Base
Sample budget=3200
2024.08
15.6
-
ReProver
2025.03
-
13.8
ReProver*
Model detail=newly pro...
2025.03
-
15.3
LeanListener
2025.03
-
14.4
Feedback
Search any
task
Search any
task