Leaderboard
Fewer prompts. More passing tests.
The demo ranks prompt quality by public checks, hidden domain checks, UX/style, and prompt efficiency. Runtime is intentionally not part of scoring.
#1
Expert ecommerce spec
98.5
Use integer-cents totals; normalize promos; cap discounts; pre-discount free shipping; enforce stock, double-submit, loading/error, ARIA, and mobile behavior.
5/5
public
10/10
hidden
9/10
ux
#2
Structured spec
84
Use a spec with states, acceptance tests, promo validation, quantity limits, cents-safe totals, and clear mobile/error behavior.
5/5
public
7/10
hidden
8/10
ux
#3
Naive prompt
66
Build an ecommerce checkout web app with cart items, quantity changes, promo code, totals, and confirmation. Make it look nice.
5/5
public
3/10
hidden
6/10
ux
Detailed ranking
#1
Expert ecommerce spec
Use integer-cents totals; normalize promos; cap discounts; pre-discount free shipping; enforce stock, double-submit, loading/error, ARIA, and mobile behavior.
public
5/5
hidden
10/10
prompts
1
98.5
#2
Structured spec
Use a spec with states, acceptance tests, promo validation, quantity limits, cents-safe totals, and clear mobile/error behavior.
public
5/5
hidden
7/10
prompts
2
84
#3
Naive prompt
Build an ecommerce checkout web app with cart items, quantity changes, promo code, totals, and confirmation. Make it look nice.
public
5/5
hidden
3/10
prompts
1
66