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.
More from coding & agent
- Solo dev runs agent swarm in Antigravity to automate SEO analysis — gaganghotra_ · 2026-11-21
- 3500-word guide: building agent evals from real LangGraph traces — strickvl · 2026-11-21
- Stanford CS329Z Lecture 9 Released: Optimizing AI Agents via Prompts vs. Weights — stanfordnlp · 2026-11-21
- Stanford CS329Z Lecture 6: AI Agent Design Patterns — ReAct, CodeAct & More — stanfordnlp · 2026-11-21
- 'Fix the Prompt Before You Fine-Tune': Stanford CS329Z's Agent Optimization Roadmap — stanfordnlp · 2026-11-21
- OpenAI agents now finish 46% of 2-4 hour tasks autonomously, up from 23% — AIFlow_ML · 2026-11-21