List your company

Reasoning on AIME 2025 (Pass@1, Cons@6, Cons@32)

58.8Pass@1SSFT-32B-GFPO
8.46421.53234.647.668Oct 1, 2025

Evaluation results

MethodLinks
SSFT-32B-GFPOTraining data type=multi-target data2025.1058.878.4883.33
SSFT-32BTraining data type=multi-target data2025.1058.1373.9486.67
SSFT-32B (random σ)Training data type=multi-target data2025.1055.167.5880
SFT-mixed-distill-32B-tagsTraining data type=multi-target data2025.1051.967076.67
SFT-OSS-distill-32BTraining data type=single-target data2025.1048.7565.4573.33
Multiverse-32BTraining data type=multi-target data2025.1045.8——
s1.1-32BTraining data type=single-target data2025.1044.2753.3363.33
Qwen2.5-32B-InstructTraining data type=single-target data2025.1010.4——