nemotron-3-ultra-550b-a55b:free vs nemotron-3.5-lightning:free
Scores
| Suite | nemotron-3-ultra-550b-a55b:free | nemotron-3.5-lightning:free | Delta |
|---|---|---|---|
| IFEval-50 prompt | 85.7% | 89.8% | -4.1 pts |
| GSM8K-50 | 78.0% | 70.0% | 8.0 pts |
| SVG total | 150/250 | 55/250 | +95 |
beach 19 vs 21
Sun low over water with a reflection path; distant objects smaller and hazier than near ones.
nvidia/nemotron-3-ultra-550b-a55b:free
19/50
nvidia/nemotron-3.5-lightning:free
21/50
clock 26 vs 0
A clock is checkable to the minute: 10:10 means the hour hand just past 10, the minute hand on 2.
nvidia/nemotron-3-ultra-550b-a55b:free
26/50
nvidia/nemotron-3.5-lightning:free
0/50
duo 31 vs 21
Two characters mid-action, not posed: a dog driving a jet ski, a raccoon holding on.
nvidia/nemotron-3-ultra-550b-a55b:free
31/50
nvidia/nemotron-3.5-lightning:free
21/50
monalisa 34 vs 6
Leonardo's portrait: three-quarter bust, folded hands, winding river landscape behind.
nvidia/nemotron-3-ultra-550b-a55b:free
34/50
nvidia/nemotron-3.5-lightning:free
6/50
pelican 40 vs 7
Everyone knows what a pelican looks like: large beak with throat pouch, long neck, webbed feet.
nvidia/nemotron-3-ultra-550b-a55b:free
40/50
nvidia/nemotron-3.5-lightning:free
7/50