CommerceAgentBench released: Qwen leads open-weight models
Alibaba_Qwen · x · 2026-09-01
Alibaba's Accio team open-sourced CommerceAgentBench, a benchmark for real commerce operations. It runs agents in high-fidelity, stateful replicas of real online services.
Key Findings:
- The best overall completion rate is only 62%, highlighting the difficulty of execution.
- Qwen3.8-Max delivered the strongest performance among open-weight models evaluated.
- The benchmark focuses on execution in real commercial workflows, not just answering questions.
Related event: Alibaba's Accio Open-Sources CommerceAgentBench for E-commerce Agents(3 posts)→
More from coding & agent
- Big Tech Is Killing Agentic AI — and Enterprises Are Letting It Happen — DavidLinthicum · 2026-10-16
- Runspore: open-source Rust workflow runtime defined in Graphviz DOT — MaxLevitskiy · 2026-10-16
- Dev builds open-source Android WhatsApp auto-responder using the Gemini API — Prince_Nebhwani · 2026-10-16
- When AI agents test your checkout, test orders shouldn't hit real inboxes — HaktanSuren · 2026-10-16
- Turn charts, logos and photos into animated videos in 5 minutes with Claude Code + Remotion — 6 copy-paste prompts — TawohAwa · 2026-10-16
- LangChain Guide: How Madrigal, Abridge and Vizient Scale Agents in Healthcare — LangChain · 2026-10-16