List your company

Mathematical Problem Solving on MATH 519 problems (test)

76.75AccuracySC-MAS
59.652464.091268.5372.9688Jan 14, 2026

Evaluation results

MethodLinks
SC-MASLLM backbone=LLM Pool, MAS=true, Routing=true2026.0176.75
MasRouterLLM backbone=LLM Pool, MAS=true, Routing=true2026.0175.42
VanillaLLM backbone=gemini-1.5-flash, MAS=false, Routing=false2026.0174.39
AgentPruneLLM backbone=gemini-1.5-flash, MAS=true, Routing=false2026.0173.54
RouterDCLLM backbone=LLM Pool, MAS=false, Routing=true2026.0173.46
GPTSwarmLLM backbone=gemini-1.5-flash, MAS=true, Routing=false2026.0173.35
AFlowLLM backbone=gpt-4o-mini, MAS=true, Routing=false2026.0173.35
PromptLLMLLM backbone=LLM Pool, MAS=false, Routing=true2026.0173.03
AFlowLLM backbone=gemini-1.5-flash, MAS=true, Routing=false2026.0172.7
RouteLLMLLM backbone=LLM Pool, MAS=false, Routing=true2026.0171.29
GPTSwarmLLM backbone=gpt-4o-mini, MAS=true, Routing=false2026.0168.85
AgentPruneLLM backbone=gpt-4o-mini, MAS=true, Routing=false2026.0168.45
FrugalGPTLLM backbone=LLM Pool, MAS=false, Routing=true2026.0167.05
VanillaLLM backbone=gpt-4o-mini, MAS=false, Routing=false2026.0166.09
VanillaLLM backbone=claude-3.5-haiku, MAS=false, Routing=false2026.0165.89
VanillaLLM backbone=llama-3.1-70b, MAS=false, Routing=false2026.0160.31