List your company

Code Generation on LiveCodeBench v6 (test) (Avg@4)

21.1Avg@4AIPO
5.6049.62713.6517.673May 8, 2026

Evaluation results

MethodLinks
AIPOPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0521.1
AIPOPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0519.2
LUFFYPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0519.2
Dr.GRPOPolicy Model=Qwen2.5-7B-Instruct2026.0518.4
GRPOPolicy Model=Qwen2.5-7B-Instruct2026.0518.1
OPSDPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0518.1
LUFFYPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0517.3
OPSDPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0517
SFTPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0516.4
PRIMEPolicy Model=Qwen2.5-7B-Instruct2026.0516.3
SFTPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0515.9
OriginalPolicy Model=Qwen2.5-7B-Instruct2026.0515.7
AIPOPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0512.4
LUFFYPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0510.8
AIPOPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.0510.1
OPSDPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.059.6
LUFFYPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.058.7
SFTPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.058
OPSDPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.057.5
SFTPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.056.2