stealthmodels.MODEL BENCHMARKS
Explore Iceman Contributor’s StealthMark scores, benchmark results and researcher observations. Read the Iceman Contributor model guide →
BENCHMARK BY BENCHMARK
Iceman ContributorOther modelsMedian
Foresight Anticipating threats and planning ahead Survived 0 of 3 
Latch Cooperative planning and learning from experience Cleared 1 of 5 
Newton's Mirror Physical, spatial and recursive reasoning 
Selfie Visual construction and creative interpretation 
Mona LisaBest placing Precise visual recall and portrait reconstruction 
Beach Creativity, perspective and visual beauty 
Ground Truth Physical reasoning, light and visual reconstruction 
Raccoon Scene composition and interacting subjects 
Pelican Subject construction and spatial relationships On every task, result quality and reasoning tokens are each compared with all measured models and weighed equally. Each dot is one model.
DATASHEET
Iceman ContributorOther modelsMedian
GAME BENCHMARKS
Anticipating threats and planning ahead
Collect coins while avoiding ghosts. Ghosts move before the player each turn, and collisions cost a life. 3 levels in sequence, up to 66 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.
Cooperative planning and learning from experience
Coordinate two robots to push numbered cores onto matching sockets. Pressure plates hold doors open; moving either robot uses one turn. 5 levels in sequence, up to 152 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.
COMPARE HEAD TO HEAD
Benchmark results
Model IDiceman-contributor
StealthMark#47of 53General11.9Visual32.2Character scenes test expression, anatomy, materials and coherent visual construction.
First run
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
First run
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
First run
A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.
First run
A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.
First run
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
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.
First run
Try another task or widen your model selection.
StealthMark scoreStealthMark 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.
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.
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 shows how well a model’s abilities carry over to original, demanding tasks, weighting every benchmark into one score from 0 to 100. Estimated means the total includes an estimate for one missing scene.
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.
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’.
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.
