List your company

Mathematical Reasoning on Game of 24 (pass@k)

100pass@1TSLM
11.634.5557.580.45Jan 30, 2026

Evaluation results

MethodLinks
TSLMevaluation_protocol=pass@12026.01100—
Procedure Cloningevaluation_protocol=pass@12026.0147—
SCevaluation_protocol=pass@12026.0117—
GRPOevaluation_protocol=pass@12026.0115—
Tree-of-Thoughtevaluation_protocol=pass@1002026.01—32