Bespoke Labs releases Multi Agent Coordination Bench

We’re releasing Multi Agent Coordination Bench, a benchmark of twelve natively multi-agent long-horizon tasks that measure the coordination capabilities of frontier models. We find that current frontier agents coordinate poorly. A team of eight agents beats a single agent, but https://t.co/1P3A2zzk8g
Views94.6k
Comments44
Reposts58
Likes509
Launched Nov 18, 2026View post
