New Multi-Agent Coordination Bench finds frontier agents coordinate poorly; only Opus gains

AlexGDimakis · x · 2026-11-21

Bespoke Labs released Multi Agent Coordination Bench, built on Harbor, with twelve natively multi-agent long-horizon tasks measuring coordination in frontier models. Key findings: current frontier agents coordinate poorly — a team of eight agents beats a single agent, but the gain comes from having more agents, not coordination. Of Opus 5.5, GPT-6.1 Sol and Gemini 4 Argon, only Opus shows signs of benefiting from actual coordination.

Original post →

More from coding & agent

coding & agent channel →