Skip to main content

← Dracon Bench leaderboard

Head-to-head

nemotron-3-nano-omni-30b-a3b-reasoning vs lfm-3-1.7b

The same frozen prompts at temperature 0, scored the same way. Every figure carries the items it was taken over, and the delta is always nemotron-3-nano-omni-30b-a3b-reasoning minus lfm-3-1.7b.

Scores

nemotron-3-nano-omni-30b-a3b-reasoning against lfm-3-1.7b.
Suitenemotron-3-nano-omni-30b-a3b-reasoninglfm-3-1.7bDelta
Overall63.8% 6 of 6· #1265.8% 5 of 6· #8-1.9 pts
IFEval-50 prompt90.0% n=10 59.6%–98.2%82.0% n=50 69.2%–90.2%+8.0 pts
IFBench-50 prompt60.0% n=10 31.3%–83.2%42.9% n=28 26.5%–60.9%+17.1 pts
MMLU-Pro-5020.0% n=10 5.7%–51.0%n/a
JSON briefs100.0% n=5 56.6%–100.0%100.0% n=5 56.6%–100.0%tie
GSM8K-5080.0% n=10 49.0%–94.3%84.0% n=50 71.5%–91.7%-4.0 pts
SVG total66/200 blind rubric10/50 blind rubric+13.0 pts

Deltas compare scores, not denominators: a 10-point gap means less when one side answered far fewer items. The n= lines keep that honest.

beach

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

nemotron-3-nano-omni-30b-a3b-reasoning

18/50

lfm-3-1.7b

unjudged

no svg

clock

A clock is checkable to the minute: 10:10 means the hour hand just past 10, the minute hand on 2.

nemotron-3-nano-omni-30b-a3b-reasoning

unjudged

no svg

lfm-3-1.7b

unjudged

no svg

duo

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

nemotron-3-nano-omni-30b-a3b-reasoning

17/50

lfm-3-1.7b

unjudged

no svg

monalisa

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

nemotron-3-nano-omni-30b-a3b-reasoning

14/50

lfm-3-1.7b

unjudged

no svg

pelican

17 vs 10

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

nemotron-3-nano-omni-30b-a3b-reasoning

17/50

lfm-3-1.7b

10/50