AI shopping agents are still struggling to return accurate and safe product advice under realistic e-commerce conditions, according to ShoppingComp, a ByteDance benchmark for LLM-powered shopping assistants. The benchmark found that even GPT-5.2 reached only 17.76% Answer Match F1 on product retrieval, while human experts scored 30.02%; on safety trap questions, GPT-5.2 scored 35.42% versus 77.08% for experts.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.