Coding on HumanEval (Solve Rate)
0.9618Solve RateCapFlow
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CapFlowType=Learning, Setting=Multi-domain, Passes=12026.02 | 0.9618 | — | |
| ScoreFlowType=Learning, Setting=Single-domain, Iterations=52026.02 | 0.9541 | — | |
| AFlowType=Refinement, Setting=Single-domain, Iterations=202026.02 | 0.9389 | — | |
| ScoreFlowType=Learning, Setting=Multi-domain, Iterations=52026.02 | 0.9389 | — | |
| CapFlowType=Learning, Setting=Cross-domain, Passes=1, Cross-domain Domain Mapping=Reason,Math->Code2026.02 | 0.9389 | — | |
| CoT-SCType=Manual, Setting=Manual2026.02 | 0.9236 | — | |
| SPPType=Manual, Setting=Manual2026.02 | 0.9236 | — | |
| CoTType=Manual, Setting=Manual2026.02 | 0.916 | — | |
| Self-RefineType=Manual, Setting=Manual2026.02 | 0.9083 | — | |
| ADASType=Refinement, Setting=Single-domain, Iterations=202026.02 | 0.9083 | — | |
| GPT-4o-miniType=Manual, Setting=Manual2026.02 | 0.9007 | — |