Accio @Accio_official · 31 Aug 2026
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 https://t.co/7fXOrSbTO5
66 022Views
85Likes
7Reposts
15Replies
4Quotes
37Bookmarks
Is that a lot?
29.9×vs this author's median2 208 views is typical
75Percentile for this authorof 4 recent posts
3.02×vs 100K–1M median21 891 views is typical
54.10%Reachviews ÷ followers
0.17%Engagement rateof viewers reacted