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

Mathematics on HMMT

77.4Accuracy

EVOLIB

Updated 19d ago

Evaluation Results

Method	Links
EVOLIB 2026.05		77.4
Best-of-N 2026.05		74.2
RSA 2026.05		67.2
DC 2026.05		66.7
ExpRAG 2026.05		60.2
Base 2026.05		57
Agent Q-Mix 2026.04		53.33
Agent Q-Mix 2026.04		50
MaAS 2026.04		46.67
TopoDIM 2026.04		46.67
GTD 2026.04		43.33
AutoGen 2026.04		43.33
G-Designer 2026.04		43.33
GTD 2026.04		43.33
TopoDIM 2026.04		40
Agent Framework 2026.04		40
GPTSwarm 2026.04		36.67
G-Designer 2026.04		36.67
AgentDropout 2026.04		36.67
GPTSwarm 2026.04		36.47
LLM-Debate 2026.04		33.33
AgentDropout 2026.04		33.33
MaAS 2026.04		33.33
Base (direct) 2026.04		33.33
LLM-Debate 2026.04		33.33
AutoGen 2026.04		33.33
LangGraph 2026.04		30
Agent Framework 2026.04		30
Base (direct) 2026.04		26.67
Lobster 2026.04		26.33
LangGraph 2026.04		26.33
Lobster 2026.04		6.67