STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Iceman Contributor vs Muse Spark 1.3

Muse Spark 1.3 leads Iceman Contributor by 20.6 points on StealthMark, 39.8 to 19.2. It leads on 7 of 9 benchmarks, including both games, and Iceman Contributor on 2. Muse Spark 1.3 scores higher on Newton's Mirror, with its largest category advantage in camera and placement.

See the difference ↘
Model guide ↗
All results ↗

Overall StealthMark

19.2/100Overall rank 47/53
39.8/100Overall rank 34/53

General Intelligence

11.7/100
38.3/100

Visual Intelligence

31.0/100
42.3/100

Reasoning efficiency

On every task, result quality and reasoning tokens are each compared with all measured models and weighed equally. Each dot is one model.

Single-step reasoning Result quality weighed against reasoning tokens on a single problem

Multi-step reasoning Result quality weighed against reasoning tokens across connected steps, as in agentic workflows

Open or local

BENCHMARK BY BENCHMARK

Where each model leads

  • Iceman Contributor
  • Muse Spark 1.3
  • Other models
  • Median

DATASHEET

Specs and pricing

Muse Spark 1.3 scores higher on StealthMark and runs 6.9× faster in our speed test.

  • Iceman Contributor
  • Muse Spark 1.3
  • Other models
  • Median
PricePer 1M output tokens, input below
Iceman Contributor: No list priceMuse Spark 1.3: $4.25$1.25 input
Context windowTokens per request, max output below
Iceman Contributor: Not publishedMuse Spark 1.3: 1M
Output speedTokens per second, our measurement
Iceman Contributor: 46tokens/sMuse Spark 1.3: 3216.9× fastertokens/s
Developer
Not publishedMeta
Released
Not published2 Sep 2026
Origin
Not publishedUnited States
Input → output
Not publishedText, image, video, audio, PDF → text

Full datasheets, every price and sourceMuse Spark 1.3 ↗

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.

Iceman Contributor 3.2/100Rank 47/47

Survived 0 of 3
Foresight: complete playing field
Level 31 ptsTurn 7 / 20

Muse Spark 1.3 64.3/100Rank 6/47

Survived 2 of 3
Foresight: complete playing field
Level 311 ptsTurn 17 / 20

Points per level

LevelIceman ContributorMuse Spark 1.3
Level 1Second Thoughts
0 ptsOut of lives
26 ptsSurvived
Level 2Pressure Pot
3 ptsOut of lives
10 ptsSurvived
Level 3Hide or Flight
1 ptsOut of lives
11 ptsOut of lives

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.

Iceman Contributor 3.6/100Rank 44/48

Cleared 1 of 5
Latch: complete playing field
Level 55 ptsTurn 25 / 40

Muse Spark 1.3 72.4/100Rank 26/483 of 5 levels

3 of 5 played
Latch: complete playing field
Level 318.8 ptsTurn 32 / 36

Points per level

LevelIceman ContributorMuse Spark 1.3
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
2.8 ptsFinished early
9.8 ptsCleared
Level 3Relay vault
2.2 ptsFinished early
18.8 ptsCleared
Level 4Passing bay
4 ptsFinished early
Pending
Level 5Second thoughts
5 ptsFinished early
Not played

Newton's Mirror

Same task instructions

Physics, perspective and recursive reflections, tested together. Explore the test ↗

The judgment

Iceman Contributor

The image provides limited evidence through rounded volume, faint wall strips and floor echoes. Its main sphere is small and low, the paint beads do not establish the required interaction history, and most of the defining mirror structure is missing.

Muse Spark 1.3

The paint state is incorrectly and poorly drawn, despite a recognizable sphere-and-paint setup. The oversized sphere, oversized compact paint bodies, and blurred wall and floor images further limit the result. Isolated reflection cues provide very little support for the required repeated virtual rooms, nested spherical imagery or emitter mapping.

Score breakdown

CategoryIceman ContributorMuse Spark 1.3
State at 600 ms0.5/256.0/25
Camera and placement2.5/158.5/15
Reflections7.5/1205.5/120
Materials and scale3.0/104.0/10
Floor-damage reward0.0/100.0/10

Benchmark task

A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.

Selfie

Different task instructions

Visual construction and creative interpretation.

The judgment

Iceman Contributor

The crystal crown, cyan eyes and blue faceting communicate an icy fantasy character. Anatomical readability is substantially weaker: the ringed torso, crowded facial construction and fingerless appendages do not resolve the requested childlike crouch or pouncing gesture. Sparse surface detail and shallow shading further limit the result.

Muse Spark 1.3

The luminous creature and geometric mirror counterpart communicate self-recognition through a coherent palette and expressive eyes. The transformed reflection is purposeful. Simple oval anatomy, ambiguous reaching-arm construction, shallow spatial staging and limited illumination of nearby surfaces keep the illustration below exceptional execution.

Score breakdown

CategoryIceman ContributorMuse Spark 1.3
Task & likeness4.0/108.0/10
Anatomy & construction3.0/105.0/10
Space & placement4.0/106.5/10
Light & reflections4.5/107.0/10
Purposeful detail4.0/106.5/10
Artistry & character4.5/105.5/10
Materials & effects4.5/106.5/10
Visual integrity4.0/107.5/10

Benchmark task

Iceman Contributor

Character scenes test expression, anatomy, materials and coherent visual construction.

Muse Spark 1.3

An imagined creature encounters its reflection. The scene tests original character design, visual self-interpretation and the relationship between a subject and its reflected image.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Iceman Contributor

The portrait retains a dark silhouette against an earthy landscape, but replication is weak. The frontal body, elongated facial proportions and undifferentiated hands lose the reference's defining pose and likeness. Basic gradients and layered hills provide some coherence, with little anatomical or painterly detail.

Muse Spark 1.3

Dark hair, a restrained smile and overlapping hands suggest Mona Lisa, but replication is weak. The face is markedly elongated, the hands are oval pads with faint finger strokes, and the atmospheric landscape is absent. Soft gradients provide basic volume, while the frontal symmetry, shallow space and sparse clothing detail limit the portrait’s drawing quality.

Score breakdown

CategoryIceman ContributorMuse Spark 1.3
Task & likeness1.5/101.0/10
Anatomy & construction1.5/101.5/10
Space & placement2.5/101.5/10
Light & reflections2.0/101.5/10
Purposeful detail2.0/101.0/10
Artistry & character2.0/101.5/10
Materials & effects2.0/101.5/10
Visual integrity3.0/103.0/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Different task instructions

Creativity, perspective and visual beauty.

The judgment

Iceman Contributor

A coherent sunset beach with recognizable animals, playful details and effective palm framing. Connected silhouettes and layered scenery support modest construction and placement credit. Jointless figures, limited foreshortening and an inadequately separated sun and reflection keep the execution basic despite its attractive color.

Muse Spark 1.3

The warm sunset, framing palms and colorful beach accessories create an appealing scene with the requested animals, birds and reflections. Construction remains schematic: the raised hand misses the kite string, and a doglike silhouette hangs above the water without clear support. The sun reflection establishes a focal path, but shadows and materials lack depth. An unexplained horizontal bar crosses the sun.

Score breakdown

CategoryIceman ContributorMuse Spark 1.3
Task & likeness7.0/106.5/10
Anatomy & construction3.5/103.0/10
Space & placement6.0/105.5/10
Light & reflections4.0/106.5/10
Purposeful detail5.5/105.0/10
Artistry & character3.5/103.5/10
Materials & effects4.5/103.0/10
Visual integrity5.0/103.5/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Different task instructions

Physical reasoning, light and visual reconstruction.

The judgment

Iceman Contributor

This benchmark has not been assessed yet.

Muse Spark 1.3

This benchmark has not been assessed yet.

Benchmark task

A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.

Raccoon

Different task instructions

Scene composition and interacting subjects.

The judgment

Iceman Contributor

The sunset palette and red hull establish an appealing setting, but the central interaction remains unresolved. Overlapping bodies obscure the dog, supported seating is unclear, and no readable paw-to-control grip demonstrates steering. Simple construction, weak environmental lighting and loosely described spray limit depth and finish.

Muse Spark 1.3

The raccoon clearly rides on the dog's back, and the dog's paws reach the jet ski controls. Expressive faces and bright colors make the scene appealing. Simplified joints, crowded steering geometry and shallow hull perspective limit construction. The sun has no corresponding water reflection, and the splash shapes convey speed more clearly than convincing displacement.

Score breakdown

CategoryIceman ContributorMuse Spark 1.3
Task & likeness2.0/108.5/10
Anatomy & construction3.0/106.5/10
Space & placement3.0/107.0/10
Light & reflections4.0/105.0/10
Purposeful detail3.5/106.5/10
Artistry & character2.5/105.5/10
Materials & effects4.0/106.0/10
Visual integrity2.5/107.5/10

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.

Pelican

Different task instructions

Subject construction and spatial relationships.

The judgment

Iceman Contributor

A recognizable pelican and bicycle sit within an appealing sunset composition. Feather contours, bill shape and atmospheric colour provide character, but disconnected-looking leg origins, unclear pedal contact and unresolved steering weaken the central riding action. Consistent wheel alignment establishes a side view without resolving the rider's support.

Muse Spark 1.3

The pelican and bicycle are immediately recognizable, with an expressive face, bold bill and cheerful composition. Both legs connect to the body and reach pedal-like supports, but articulation, saddle support and wing contact with the handlebar remain unclear. Wheel alignment and layering are coherent. Simple landscape shapes, generic shadows and limited material variation constrain the finish.

Score breakdown

CategoryIceman ContributorMuse Spark 1.3
Task & likeness4.0/108.5/10
Anatomy & construction3.5/106.0/10
Space & placement3.5/107.0/10
Light & reflections5.0/106.0/10
Purposeful detail4.5/107.0/10
Artistry & character3.5/105.5/10
Materials & effects4.0/106.5/10
Visual integrity3.0/107.0/10

Benchmark task

A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.