List your company

Puzzle Reasoning on Reasoning Gym (test)

17.8Avg@4AIPO
3.5527.25110.9514.649May 8, 2026

Evaluation results

MethodLinks
AIPOPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0517.8
AIPOPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0516
LUFFYPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0515.7
Dr.GRPOPolicy Model=Qwen2.5-7B-Instruct2026.0515
OPSDPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0514.7
GRPOPolicy Model=Qwen2.5-7B-Instruct2026.0514.5
LUFFYPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0513.9
AIPOPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0513.3
OPSDPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0512.4
PRIMEPolicy Model=Qwen2.5-7B-Instruct2026.0512.2
LUFFYPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0511.9
AIPOPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.0511
SFTPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0510.5
OPSDPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0510.4
SFTPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.059.8
OriginalPolicy Model=Qwen2.5-7B-Instruct2026.059.6
SFTPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.056
LUFFYPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.054.9
OPSDPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.054.6
SFTPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.054.1