Math on MATH (Solve Rate, Executability)
59.87Solve RateCapFlow
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CapFlowType=Learning, Setting=Multi-domain, Passes=12026.02 | 59.87 | — | |
| ScoreFlowType=Learning, Setting=Single-domain, Iterations=52026.02 | 59.25 | — | |
| ScoreFlowType=Learning, Setting=Multi-domain, Iterations=52026.02 | 57.81 | — | |
| AFlowType=Refinement, Setting=Single-domain, Iterations=202026.02 | 57.4 | — | |
| CapFlowType=Learning, Setting=Cross-domain, Passes=1, Cross-domain Domain Mapping=Reason,Code->Math2026.02 | 54.32 | — | |
| CoT-SCType=Manual, Setting=Manual2026.02 | 53.7 | — | |
| CoTType=Manual, Setting=Manual2026.02 | 53.29 | — | |
| SPPType=Manual, Setting=Manual2026.02 | 52.88 | — | |
| ADASType=Refinement, Setting=Single-domain, Iterations=202026.02 | 52.67 | — | |
| GPT-4o-miniType=Manual, Setting=Manual2026.02 | 51.64 | — | |
| Self-RefineType=Manual, Setting=Manual2026.02 | 50.2 | — |