List your company
ResearchFormerly WizWand

Mathematical Reasoning on LiveMathBench v202505 (test)

17.5Avg@4AIPO
4.2927.72111.1514.579May 8, 2026
Updated 5mo ago

Evaluation results

MethodLinks
AIPOPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0517.5
LUFFYPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0515.1
AIPOPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0514.9
OPSDPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0514.2
Dr.GRPOPolicy Model=Qwen2.5-7B-Instruct2026.0514
GRPOPolicy Model=Qwen2.5-7B-Instruct2026.0513.9
AIPOPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0513.3
LUFFYPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0513.2
OPSDPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0512.8
SFTPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0512.5
PRIMEPolicy Model=Qwen2.5-7B-Instruct2026.0511.5
SFTPolicy Model=Qwen2.5-7B-Instruct, Collaborator Model=Qwen2.5-7B-Instruct2026.0511.1
OriginalPolicy Model=Qwen2.5-7B-Instruct2026.0510.8
AIPOPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.0510.8
LUFFYPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.0510.8
OPSDPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.059.5
OPSDPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.057
SFTPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Qwen3-30B-A3B-Instruct-25072026.057
SFTPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.055.1
LUFFYPolicy Model=Llama3.2-3B-Instruct, Collaborator Model=Llama3.2-3B-Instruct2026.054.8