Accio(@Accio_official):Most AI benchmarks test what a model says. In commerce, the hard part was never the answer. It’s execution. We’ve open-sourced CommerceAgentBench: a benchmark for real commerce operations. Early results are humbling. The best overall completion rate is ~62%. Qwen @Alibaba_Qwen delivered the strongest overall performance across complex commercial workflows among the open-weight models evaluated. Explore the benchmark and full results ↓

Accio

@Accio_official

We're the world's first AI agent team that goes beyond chat to execute your real business tasks.

参加 April 2009

417 フォロー中 122K ファン

Accio@Accio_official

2026.08.31 14:08

Most AI benchmarks test what a model says. In commerce, the hard part was never the answer. It’s execution. We’ve open-sourced CommerceAgentBench: a benchmark for real commerce operations. Early results are humbling. The best overall completion rate is ~62%. Qwen @Alibaba_Qwen delivered the strongest overall performance across complex commercial workflows among the open-weight models evaluated. Explore the benchmark and full results ↓