List your company

Math on MATH (Solve Rate, Executability)

59.87Solve RateCapFlow
49.813252.424155.03557.6459Feb 11, 2026

Evaluation results

MethodLinks
CapFlowType=Learning, Setting=Multi-domain, Passes=12026.0259.87—
ScoreFlowType=Learning, Setting=Single-domain, Iterations=52026.0259.25—
ScoreFlowType=Learning, Setting=Multi-domain, Iterations=52026.0257.81—
AFlowType=Refinement, Setting=Single-domain, Iterations=202026.0257.4—
CapFlowType=Learning, Setting=Cross-domain, Passes=1, Cross-domain Domain Mapping=Reason,Code->Math2026.0254.32—
CoT-SCType=Manual, Setting=Manual2026.0253.7—
CoTType=Manual, Setting=Manual2026.0253.29—
SPPType=Manual, Setting=Manual2026.0252.88—
ADASType=Refinement, Setting=Single-domain, Iterations=202026.0252.67—
GPT-4o-miniType=Manual, Setting=Manual2026.0251.64—
Self-RefineType=Manual, Setting=Manual2026.0250.2—