flint-v1.0:free vs free
Scores
| Suite | flint-v1.0:free | free | Delta |
|---|---|---|---|
| IFEval-50 prompt | 93.3% | 87.8% | 5.6 pts |
| GSM8K-50 | 88.1% | 92.0% | -3.9 pts |
| SVG total | 144/250 | 145/250 | -1 |
beach 31 vs 30
Sun low over water with a reflection path; distant objects smaller and hazier than near ones.
recursive/flint-v1.0:free
31/50
kilo-auto/free
30/50
clock 37 vs 43
A clock is checkable to the minute: 10:10 means the hour hand just past 10, the minute hand on 2.
recursive/flint-v1.0:free
37/50
kilo-auto/free
43/50
duo 26 vs 31
Two characters mid-action, not posed: a dog driving a jet ski, a raccoon holding on.
recursive/flint-v1.0:free
26/50
kilo-auto/free
31/50
monalisa 26 vs 14
Leonardo's portrait: three-quarter bust, folded hands, winding river landscape behind.
recursive/flint-v1.0:free
26/50
kilo-auto/free
14/50
pelican 24 vs 27
Everyone knows what a pelican looks like: large beak with throat pouch, long neck, webbed feet.
recursive/flint-v1.0:free
24/50
kilo-auto/free
27/50