Benchmark
Composio Benchmark
Evaluation of agents performing stateful tool-use and multi-app workflows.
Published leaderboard
Explore scores and evaluation settings on the publisher’s leaderboard.
Open leaderboardCoverage
The official task collection contains 30 tasks spanning multi-app workflows, reconciliation, source sweeps, guarded writes, batching, and pagination.
Methodology
A deterministic verifier checks the final state of touched apps and requested responses; every required check must pass.