QuickCart
The QuickCart platform connects users with local restaurants and merchants, allowing them to explore menus, place orders, and choose delivery or pickup options, all from a single interface.
Overview
FeaturesProduct Listing, Stock Management, Browse and Search…
Tasks35 prompts and verifiers
Leaderboard
Overall Pass Rate (pass@8)
claude-sonnet-4
40.71%
gpt-computer-use-preview
33.57%
gemini-2
32.14%
Evaluation Results
Easy: 66.7% < Pass@8 ≤ 100%
Medium: 33.3% < Pass@8 < 66.6% AND Median Steps ≤ 80
Hard: Pass@8 ≤ 33.3% OR Median Steps > 80
This model: 10 easy · 8 medium · 17 hard tasks
#1claude-sonnet-4
Pass rate: 40.71%
Capabilities
Product Management
Product Listing
Create and manage product catalog
Inventory
Stock Management
Track availability and stock levels
Product Discovery
Browse and Search
Navigate products by category or keyword
Cart Management
Add / Remove Items
Manage items in shopping cart
Checkout
Order Placement
Complete checkout with address and payment
Order Management
View Orders
Track and manage customer orders
Promotions
Coupons & Discounts
Apply promotional pricing rules
Demo Execution
Watch how an AI agent interacts with this environment
Prompt
I'm in a rush and need some beauty essentials. Go to the retail section and find me a beauty store nearby that can deliver in under 30 minutes. I mainly want Beija Flor Jet Set and eye lashes. If the store has any popular deals add first item there too. Add them all to my cart.
Loading timeline...