The Eval Index / Agent Eval / #258
AGI-Eval-Official/CATArena
by AGI-Eval-Official · Agent Eval · updated 10mo ago
CATArena is an engineering-level tournament evaluation platform for Large Language Model-driven code agents (LLM-driven code agents), based on an iterative competitive peer learning framework.
22
momentum
69
stars
11
forks
#258
rank