List your company

Instruction Following on IFEVAL (SSR, HSR)

75.7SSRPT-GRPO
53.3459.14564.9570.755Jun 4, 2026

Evaluation results

MethodLinks
PT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.0675.765.8
MDP-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.0675.364.1
DA-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.0675.264.7
DA-PT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.0674.864.3
MT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.0673.963.7
GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.0673.762.4
DA-PT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.0671.560.4
MDP-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.0671.359.8
DA-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.0671.262.5
PT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.0670.161.3
MT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.0668.159.1
GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.0666.158.5
BaselineModel=Gemma-2-2B-Instruct, Group Size (G)=82026.0656.745.1
BaselineModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.0654.246.8