Multi Agent Coordination Benchmark
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
MAC Bench is a new benchmark of twelve simulated tasks that measures whether teams of AI agents coordinate well, separating the gain from communication from the gain of simply adding agents. Its tasks are built so each agent depends on its teammates' work.