Skip to main content

← Dracon Bench leaderboard

flint-v1.0:free vs nemotron-3-nano-omni-30b-a3b-reasoning:free

Scores

Suiteflint-v1.0:freenemotron-3-nano-omni-30b-a3b-reasoning:freeDelta
IFEval-50 prompt93.3%89.8%3.5 pts
GSM8K-5088.1%78.0%10.1 pts
SVG total144/250104/250+40

beach 31 vs 17

Sun low over water with a reflection path; distant objects smaller and hazier than near ones.

recursive/flint-v1.0:free

31/50

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

17/50

clock 37 vs 31

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

12 1 2 3 4 5 6 7 8 9 10 11 DRACON

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

31/50

12 1 2 3 4 5 6 7 8 9 10 11 DRACON

duo 26 vs 20

Two characters mid-action, not posed: a dog driving a jet ski, a raccoon holding on.

recursive/flint-v1.0:free

26/50

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

20/50

monalisa 26 vs 16

Leonardo's portrait: three-quarter bust, folded hands, winding river landscape behind.

recursive/flint-v1.0:free

26/50

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

16/50

pelican 24 vs 20

Everyone knows what a pelican looks like: large beak with throat pouch, long neck, webbed feet.

recursive/flint-v1.0:free

24/50

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

20/50