Thor + expert iteration on autoformalised theorems
Reported on 4 benchmarks across 2 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Miscellaneous4 results
- Pass@1· uses extra data35.2best: 52.94 (Kimina-Prover-Preview)
- cumulative· uses extra data35.2best: 80.74 (Kimina-Prover-Preview)
- Pass@1· uses extra data35.2best: 52.94 (Kimina-Prover-Preview)
- cumulative· uses extra data35.2best: 80.74 (Kimina-Prover-Preview)