List your company

Mathematical Reasoning on AIME 2024 (pass@K)

86.67Pass@KOriginal
62.396468.69827581.3018Oct 1, 2025

Evaluation results

MethodLinks
OriginalBackbone=DSQwen-14B2025.1086.67
STARBackbone=DSQwen-14B2025.1086.67
SafeChainBackbone=DSQwen-14B2025.1086.67
DAPOBackbone=DSQwen-14B2025.1086.67
RECAPBackbone=DSQwen-14B2025.1086.67
SFTBackbone=DSQwen-14B2025.1083.33
OriginalBackbone=DSLlama-8B2025.1070
SafeChainBackbone=DSLlama-8B2025.1070
RECAPBackbone=DSLlama-8B2025.1070
STARBackbone=DSLlama-8B2025.1066.67
DAPOBackbone=DSLlama-8B2025.1066.67
SFTBackbone=DSLlama-8B2025.1063.33