Mathematical Problem Solving on MATH 519 problems (test)
76.75AccuracySC-MAS
Evaluation Results
| Method | Links | |
|---|---|---|
| SC-MASLLM backbone=LLM Pool, MAS=true, Routing=true2026.01 | 76.75 | |
| MasRouterLLM backbone=LLM Pool, MAS=true, Routing=true2026.01 | 75.42 | |
| VanillaLLM backbone=gemini-1.5-flash, MAS=false, Routing=false2026.01 | 74.39 | |
| AgentPruneLLM backbone=gemini-1.5-flash, MAS=true, Routing=false2026.01 | 73.54 | |
| RouterDCLLM backbone=LLM Pool, MAS=false, Routing=true2026.01 | 73.46 | |
| GPTSwarmLLM backbone=gemini-1.5-flash, MAS=true, Routing=false2026.01 | 73.35 | |
| AFlowLLM backbone=gpt-4o-mini, MAS=true, Routing=false2026.01 | 73.35 | |
| PromptLLMLLM backbone=LLM Pool, MAS=false, Routing=true2026.01 | 73.03 | |
| AFlowLLM backbone=gemini-1.5-flash, MAS=true, Routing=false2026.01 | 72.7 | |
| RouteLLMLLM backbone=LLM Pool, MAS=false, Routing=true2026.01 | 71.29 | |
| GPTSwarmLLM backbone=gpt-4o-mini, MAS=true, Routing=false2026.01 | 68.85 | |
| AgentPruneLLM backbone=gpt-4o-mini, MAS=true, Routing=false2026.01 | 68.45 | |
| FrugalGPTLLM backbone=LLM Pool, MAS=false, Routing=true2026.01 | 67.05 | |
| VanillaLLM backbone=gpt-4o-mini, MAS=false, Routing=false2026.01 | 66.09 | |
| VanillaLLM backbone=claude-3.5-haiku, MAS=false, Routing=false2026.01 | 65.89 | |
| VanillaLLM backbone=llama-3.1-70b, MAS=false, Routing=false2026.01 | 60.31 |