Automated Theorem Proving on CombiBench Hard Mode
10Total Solved (Pass@32)DAP
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DAPAgent Usage=w/o Agent, Pass@k=Pass@322026.04 | 10 | 2 | |
| DAPAgent Usage=w/ Agent, Pass@k=Pass@322026.04 | 9 | 1 | |
| Kimina-Prover PreviewPass@k=Pass@322026.04 | 8 | — |