The Eval Index / Agent Eval / #133
suyoumo/ClawProBench
by suyoumo · Agent Eval · updated 2mo ago
ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.
54
momentum
829
stars
54
forks
#133
rank
agentbenchmarkevaluationharnessleaderboardllmopenclaw
View on GitHub →