Share your thoughts, 1 month free Claude Pro on usSee more

Mathematics on AIME 26

70Accuracy

AutoGen

Updated 16d ago

Evaluation Results

Method	Links
AutoGen 2026.04		70
Agent Framework 2026.04		63.33
Lobster 2026.04		60
LangGraph 2026.04		60
Agent Q-Mix 2026.04		60
AutoGen 2026.04		60
Agent Q-Mix 2026.04		60
Agent Framework 2026.04		56.67
GTD 2026.04		46.67
GPTSwarm 2026.04		43.33
G-Designer 2026.04		43.33
TopoDIM 2026.04		43.33
GTD 2026.04		40
GPTSwarm 2026.04		40
MaAS 2026.04		40
LLM-Debate 2026.04		36.67
G-Designer 2026.04		36.67
Lobster 2026.04		36.67
LangGraph 2026.04		36.67
MaAS 2026.04		33.33
AgentDropout 2026.04		33.33
AgentDropout 2026.04		30
TopoDIM 2026.04		26.67
Base (direct) 2026.04		20
LLM-Debate 2026.04		20
Base (direct) 2026.04		13.33