crouton-alpha vs flint-v1.0:free
Scores
| Suite | crouton-alpha | flint-v1.0:free | Delta |
|---|---|---|---|
| IFEval-50 prompt | 83.3% | 93.3% | -10.0 pts |
| GSM8K-50 | n/a | 88.1% | |
| SVG total | n/a | 144/250 |
beach
Sun low over water with a reflection path; distant objects smaller and hazier than near ones.
stealth/crouton-alpha
unjudged
no svg
recursive/flint-v1.0:free
31/50
clock
A clock is checkable to the minute: 10:10 means the hour hand just past 10, the minute hand on 2.
stealth/crouton-alpha
unjudged
no svg
recursive/flint-v1.0:free
37/50
duo
Two characters mid-action, not posed: a dog driving a jet ski, a raccoon holding on.
stealth/crouton-alpha
unjudged
no svg
recursive/flint-v1.0:free
26/50
monalisa
Leonardo's portrait: three-quarter bust, folded hands, winding river landscape behind.
stealth/crouton-alpha
unjudged
no svg
recursive/flint-v1.0:free
26/50
pelican
Everyone knows what a pelican looks like: large beak with throat pouch, long neck, webbed feet.
stealth/crouton-alpha
unjudged
no svg
recursive/flint-v1.0:free
24/50