Skip to main content

← Dracon Bench leaderboard

liquid/lfm-3-1.7b:free

Tested First tested 2026-11-11 · OpenRouter free lane

Liquid AI's tiny LFM 3 1.7B: IFEval-50 83.7%, GSM8K-50 84.0% with zero failures, SVG 10/50 over 1 judged test. Heavy reasoning traces burned whole budgets: 1 IFEval prompt and 4 of 5 SVG briefs unrecoverable even at 32k, counted as failures. Strong small-model reasoning signal, weak long-form emission.

Scores

SuiteScore
IFEval-50 prompt-strict83.7% (n=49)
IFEval-50 instruction-strict89.6% (n=49)
GSM8K-5084.0% (42/50)
SVG blind rubric10/50

Artifacts

Blind-judged by nvidia/nemotron-3.5-super-vl:free: the judge saw the brief and the rendered image only, never the model name. Briefs are frozen; expand one to read it.

beach

no svg

Brief

Draw a beautiful sunset beach scene: a large sun sitting low over the sea with a shimmering reflection path on the water, a leaning palm tree silhouette on the left, two dolphins arcing out of the waves, a small sailboat on the right, birds in the sky, sandy foreground with a starfish. Warm oranges and pinks fading to teal. Coherent perspective: distant objects smaller and hazier than near ones. Output: exactly one self-contained SVG (viewBox "0 0 800 600", no external references) inside a single ```svg fenced block. Short prose outside the fence is allowed.

clock

no svg

Brief

Draw a round wall clock face showing exactly 10:10: a circular dial with all 12 hour numerals in the correct positions, minute tick marks, an hour hand pointing just past 10, a minute hand pointing exactly at 2, and a thin second hand pointing at 6. The word DRACON in small capitals under the center. Dark rim, light face, flat vector style, centered composition. Output: exactly one self-contained SVG (viewBox "0 0 800 600", no external references) inside a single ```svg fenced block. Short prose outside the fence is allowed.

duo

no svg

Brief

Draw a comical scene: a dog driving a jet ski at speed, paws on the handlebars, with a raccoon riding behind holding on, both leaning into a turn. Sea spray behind the jet ski, sun and clouds in the sky, a distant shoreline. Both characters must be clearly doing something, not just posed side by side. Bright cartoon vector style. Output: exactly one self-contained SVG (viewBox "0 0 800 600", no external references) inside a single ```svg fenced block. Short prose outside the fence is allowed.

monalisa

no svg

Brief

Redraw the Mona Lisa as a flat vector portrait, bust composition: a seated woman in three-quarter view facing the viewer, dark dress with neckline detail, hands folded at the bottom edge, soft enigmatic smile, hair parted in the middle. Behind her a hazy landscape with a winding river, a bridge on the right, and blue mountains. Muted greens, browns, and smoky blues. Output: exactly one self-contained SVG (viewBox "0 0 800 600", no external references) inside a single ```svg fenced block. Short prose outside the fence is allowed.

pelican · 10/50

Brief fidelity (1/10)
The image does not clearly depict a brown pelican; the requested side-profile stance, throat pouch, folded wing, and webbed feet are missing or unrecognizable.
Construction (2/10)
The body, neck, and head are crude abstract shapes that do not assemble into coherent pelican anatomy.
Composition (3/10)
A horizon and ground plane are present, but the subject is small, oddly placed, and fails to occupy the frame as a full-body standing bird.
Detail finish (2/10)
The artwork is extremely minimal with no shading, textures, or finishing touches beyond flat shapes.
Visual appeal (2/10)
The illustration lacks charm and does not read as a confident or appealing pelican depiction.
Brief

Draw a brown pelican standing in side profile, facing left, full body visible: large beak with throat pouch, long neck, folded wing, webbed feet on flat ground. Simple sky background with a hint of sea on the horizon. Flat vector style, clean shapes, limited palette. Output: exactly one self-contained SVG (viewBox "0 0 800 600", no external references) inside a single ```svg fenced block. Short prose outside the fence is allowed.

Compare with

Evidence and notes

  • 4 of 5 SVG briefs unrecoverable: reasoning trace exhausted the 32k token budget (beach/clock failed three attempts)
  • 3 truncated SVG stubs pruned and redone at 32k per the flint precedent; only pelican completed
  • 1 IFEval prompt unrecoverable under the token budget, counted as failure