SelfieVisual construction
and creative interpretation
Benchmark task
Character scenes test expression, anatomy, materials and coherent visual construction.
First run
MODEL BENCHMARKS
Crouton Alpha: Pelican
Explore Crouton Alpha’s StealthMark scores, benchmark results and researcher observations. Read the Crouton Alpha model guide →
StealthMark↗48.0/100Overall benchmark scoreGeneral Intelligence↗43.5/100Spatial & physical reasoningVisual Intelligence↗56.0/100Visual construction & detail
DATASHEET
Crouton Alpha speed
Crouton AlphaOther modelsMedian
Output speedTokens per second, our measurement175 tokens/sFaster than 35 of 50 others
Models All
Filter models
Benchmark results
Model
SelfieVisual construction
and creative interpretationVisualGeneral
Mona LisaPrecise visual recall
and portrait reconstructionVisualGeneral
BeachCreativity, perspective
and visual beautyVisualGeneral
Newton's MirrorPhysical, spatial
and recursive reasoningVisualGeneral
Ground TruthPhysical reasoning, light
and visual reconstructionVisualGeneral
RaccoonScene composition
and interacting subjectsVisualGeneral
PelicanSubject construction and spatial relationshipsVisualGeneral
ForesightAnticipating threats
and planning aheadGeneralLearning
LatchCooperative planning
and learning from experienceGeneralLearning
No result yet
Mona LisaPrecise visual recall
and portrait reconstruction
Benchmark task
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
First run
No result yet
BeachCreativity, perspective
and visual beauty
Benchmark task
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
First run
No result yet
Newton's MirrorPhysical, spatial
and recursive reasoning
Benchmark task
A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.
First run
No result yet
Ground TruthPhysical reasoning, light
and visual reconstruction
Benchmark task
A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.
First run
No result yet
RaccoonScene composition
and interacting subjects
Benchmark task
A jet-ski scene pairs a canine driver with a raccoon passenger. It tests the placement and contact of interacting subjects, along with vehicle construction.
First run
No result yet
PelicanSubject construction and spatial relationships
Benchmark task
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.
First run
No result yet
ForesightAnticipating threats
and planning ahead
Survived 1 of 3
Level 39 ptsTurn 20 / 20
LatchCooperative planning
and learning from experience
Cleared 4 of 5
Level 520.2 ptsTurn 29 / 40
No results in this view.
Try another task or widen your model selection.
StealthMark score
StealthMark measures how well a model’s abilities carry over to original, demanding tasks it could not have trained for: physical and spatial reasoning, planning across many steps, and precise visual work. How StealthMark works explains every benchmark, what it tests and why it is hard.
General Intelligence
The ability to reason, plan, solve problems and understand how things relate and behave. A high score means it thinks hard problems through, from careful analysis to plans that span many steps.
Visual Intelligence
The ability to understand visual intent and turn ideas, descriptions and plans into coherent, effective visuals. A high score means design ideas come out the way you meant them, in illustrations, icons, diagrams or interface visuals.
Overall score
Overall shows how well a model’s abilities carry over to original, demanding tasks, weighting every benchmark into one score. Estimated means the total includes an estimate for one missing scene.
Judging
Scores reflect how well each result meets the benchmark requirements. Game scores come from the recorded play: the points earned on each level and how each level ended. How StealthMark keeps scores honest.
Games
Each game is a sequence of levels, and earlier moves carry into later levels. A level that was not played is shown as not played and never counts as zero. Play every level of Latch or Foresight yourself to get a score calculated like the models’.
Reasoning efficiency
Good results with little thinking score high. On each task, a model’s result and reasoning tokens are compared with every other model and combined with the Balanced Integration Score (Liesefeld & Janczyk, 2019); 50 is average. Single step shows how much reasoning a model needs to understand and solve one problem, multi-step how efficiently it keeps working on a task by building on its earlier reasoning, as in agentic workflows. Not part of StealthMark.
Cost efficiency
How much StealthMark a model delivers for its money, in StealthMark points per dollar: its overall score divided by what one benchmark task costs it on average. The cost is what our runs were charged, or their tokens at the model’s list price; benchmarks a model has not run yet are estimated from its other costs. Like StealthMark, it is absolute and compares with no other model. Not part of StealthMark.