free vs lfm-2.5-2.6b:free
Scores
| Suite | free | lfm-2.5-2.6b:free | Delta |
|---|---|---|---|
| IFEval-50 prompt | 87.8% | 87.8% | 0.0 pts |
| GSM8K-50 | 92.0% | 74.0% | 18.0 pts |
| SVG total | 145/250 | 68/200 | +77 |
beach 30 vs 15
Sun low over water with a reflection path; distant objects smaller and hazier than near ones.
kilo-auto/free
30/50
liquid/lfm-2.5-2.6b:free
15/50
clock
A clock is checkable to the minute: 10:10 means the hour hand just past 10, the minute hand on 2.
kilo-auto/free
43/50
liquid/lfm-2.5-2.6b:free
unjudged
no svg
duo 31 vs 26
Two characters mid-action, not posed: a dog driving a jet ski, a raccoon holding on.
kilo-auto/free
31/50
liquid/lfm-2.5-2.6b:free
26/50
monalisa 14 vs 11
Leonardo's portrait: three-quarter bust, folded hands, winding river landscape behind.
kilo-auto/free
14/50
liquid/lfm-2.5-2.6b:free
11/50
pelican 27 vs 16
Everyone knows what a pelican looks like: large beak with throat pouch, long neck, webbed feet.
kilo-auto/free
27/50
liquid/lfm-2.5-2.6b:free
16/50