List your company

Reasoning on MATH 500 (Pass@1, Cons@6, Cons@32)

92.16Pass@1s1.1-32B
79.929683.104886.2889.4552Oct 1, 2025

Evaluation results

MethodLinks
s1.1-32BTraining data type=single-target data2025.1092.1695.694.8
Multiverse-32BTraining data type=multi-target data2025.1091.8——
SSFT-32BTraining data type=multi-target data2025.1090.0296.4796.8
SSFT-32B (random σ)Training data type=multi-target data2025.1089.9595.6795.6
SSFT-32B-GFPOTraining data type=multi-target data2025.1089.995.7396.8
SFT-OSS-distill-32BTraining data type=single-target data2025.1089.5495.4796
SFT-mixed-distill-32B-tagsTraining data type=multi-target data2025.1088.4995.8896.2
Qwen2.5-32B-InstructTraining data type=single-target data2025.1080.4——