List your company

Accuracy on Brumo 2025 (Mathematical Reasoning)

54.79AccuracyDelTA
35.726840.675945.62550.5741May 20, 2026

Evaluation results

MethodLinks
DelTABackbone=Qwen3-14B-Base, Fine-tuning (FT)=false2026.0554.79
DAPOBackbone=Qwen3-14B-Base, Fine-tuning (FT)=true2026.0552.08
FIPOBackbone=Qwen3-14B-Base, Fine-tuning (FT)=false2026.0552.08
SAPOBackbone=Qwen3-14B-Base, Fine-tuning (FT)=false2026.0550.21
DAPOBackbone=Qwen3-14B-Base, Fine-tuning (FT)=false2026.0548.13
DelTABackbone=Qwen3-8B-Base, Fine-tuning (FT)=false2026.0544.79
SAPOBackbone=Qwen3-8B-Base, Fine-tuning (FT)=false2026.0539.37
DAPOBackbone=Qwen3-8B-Base, Fine-tuning (FT)=true2026.0539.17
FIPOBackbone=Qwen3-8B-Base, Fine-tuning (FT)=false2026.0537.71
DAPOBackbone=Qwen3-8B-Base, Fine-tuning (FT)=false2026.0536.46