STEALTHMARK · HEAD TO HEAD
All comparisons ↗GPT-5.5 vs Muse Spark Open
Muse Spark Open leads GPT-5.5 by 12.8 points on StealthMark, 44.1 to 31.3. It leads on 6 of the 7 benchmarks with results for both and GPT-5.5 on 1. Muse Spark Open scores higher on Ground Truth.
See the difference ↘Overall StealthMark
General Intelligence
Visual Intelligence
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
- GPT-5.5Multi-step reasoning not measured
- Muse Spark Open
BENCHMARK BY BENCHMARK
Where each model leads
- GPT-5.5
- Muse Spark Open
- Other models
- Median
Games
SVG
DATASHEET
Specs and pricing
Muse Spark Open scores higher on StealthMark, is 7.1× cheaper per output token and runs 1.9× faster in our speed test. Both take about 1.05M tokens of context.
- GPT-5.5
- Muse Spark Open
- Other models
- Median
- Developer
- OpenAIMeta
- Released
- 23 Apr 202615 Oct 2026
- Origin
- United StatesBoth
- Input → output
- Text, image → textText, image, audio, video → text
- Architecture
- Not publishedSparse mixture-of-experts Transformer with perception encoders; 62 decoder layers, 256 experts with 8 selected per token, grouped-query attention and sliding-window/full-attention layers.
Full datasheets, every price and sourceGPT-5.5 ↗Muse Spark Open ↗
Foresight
Play Foresight yourselfAnticipating 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.
Muse Spark Open 29.4/100Rank 34/47

Points per level
Latch
Play Latch yourselfCooperative 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.
GPT-5.5No run
Muse Spark Open 75.7/100Rank 12/48

Points per level
Newton's Mirror
Same task instructionsPhysics, perspective and recursive reflections, tested together. Explore the test ↗
GPT-5.5 22.7/100 Rank 35/53

Muse Spark Open 19.6/100 Rank 39/53

The judgment
GPT-5.5
The paint ordering and separate black bead support part of the physical state, but adhesion and rotational transport remain only partly established. The sweeping cyan arc and long crimson lobes do not clearly communicate the limited time since their respective impacts. The main sphere is too large and too low, and the black bead is below its required projected position. Displaced isolated sphere images, a flattened floor echo and missing recursive, nested and emitter reflections provide little coherent optical structure. The colored paint is excessively bulky for the specified quantities.
Muse Spark Open
The airborne black blob and deformed paint support the broad contact sequence, although cyan attachment and wheel-directed transport remain partial. The sphere and black blob have substantial framing errors. The dominant limitation is the largely absent mirror system: faint wall circles and isolated highlights provide little evidence of recursive room geometry or curved nested reflections. Oversized compact paint features and diffuse material treatment further limit credit.
Score breakdown
| Category | GPT-5.5 | Muse Spark Open |
|---|---|---|
| State at 600 ms | 15.0/25 | 14.0/25 |
| Camera and placement | 6.0/15 | 6.0/15 |
| Reflections | 5.0/120 | 8.0/120 |
| Materials and scale | 6.0/10 | 3.5/10 |
| Floor-damage reward | 0.0/10 | 0.0/10 |
Benchmark task
A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.
Selfie
Different task instructionsVisual construction and creative interpretation.
GPT-5.5 41.9/100 Rank 48/53

Muse Spark Open 52.1/100 Rank 40/53

The judgment
GPT-5.5
Six pale, scaled lobes form a balanced radial arrangement, but they remain separate capsules rather than an interlocking serpent knot. There are no crossings, alternating overlaps, or crisp inner bends; the central hexagon is an isolated outline. Small outward-facing heads sit within the lobes without integrated necks. Soft shading and tidy contours provide some finish, while repetitive oval scales and cartoon faces limit organic credibility.
Muse Spark Open
The rounded silhouette and asymmetric expression make an appealing baby elephant, supported by a quiet background and grounding shadow. The protective action remains difficult to read: forefeet cannot be confidently traced into a grip, and seed contact is crowded by fine lines. Controlled simple shapes provide charm, but limited anatomical clarity, shading and surface detail leave the execution uneven.
Score breakdown
| Category | GPT-5.5 | Muse Spark Open |
|---|---|---|
| Task & likeness | 3.0/10 | 5.0/10 |
| Anatomy & construction | 3.0/10 | 4.5/10 |
| Space & placement | 5.0/10 | 6.0/10 |
| Light & reflections | 5.0/10 | 5.0/10 |
| Purposeful detail | 4.5/10 | 6.0/10 |
| Artistry & character | 4.0/10 | 5.0/10 |
| Materials & effects | 4.5/10 | 5.0/10 |
| Visual integrity | 7.0/10 | 6.5/10 |
Benchmark task
GPT-5.5
A pale serpent woven into an interlocking knot tests connected anatomy, repeated structure and readable overlaps. Organic surface detail must work with the overall geometry.
Muse Spark Open
A small elephant protecting a delicate seed tests expressive anatomy, physical contact and contrasting organic materials.
Mona Lisa
Different task instructionsPrecise visual recall and portrait reconstruction.
GPT-5.5 17.3/100 Rank 43/53

Muse Spark Open 37.8/100 Rank 27/53

The judgment
GPT-5.5
The veil, restrained smile, crossed hands and muted landscape establish Mona Lisa references. The oversized frontal face and schematic features weaken likeness and expression, while fingerless tapered hand shapes leave anatomy unresolved. Clean contours and balanced framing provide coherence, but sparse garment detail, broad landscape bands and shallow shading limit the portrait's sophistication.
Muse Spark Open
A recognizable, orderly interpretation with clean major contours, connected body forms and modest facial shading. Wide eyes, frontal symmetry and schematic hands limit likeness and expression. Layered scenery establishes basic depth, but shallow arm overlaps, flat clothing and sparse fine detail keep the execution basic and uneven.
Score breakdown
| Category | GPT-5.5 | Muse Spark Open |
|---|---|---|
| Task & likeness | 1.5/10 | 3.0/10 |
| Anatomy & construction | 1.5/10 | 3.0/10 |
| Space & placement | 1.5/10 | 5.0/10 |
| Light & reflections | 2.0/10 | 4.5/10 |
| Purposeful detail | 2.5/10 | 4.0/10 |
| Artistry & character | 1.5/10 | 3.0/10 |
| Materials & effects | 2.0/10 | 4.0/10 |
| Visual integrity | 1.5/10 | 6.0/10 |
Benchmark task
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
Beach
Different task instructionsCreativity, perspective and visual beauty.
GPT-5.5 34.9/100 Rank 49/53

Muse Spark Open 64.2/100 Rank 25/53

The judgment
GPT-5.5
The sunset, palms, birds, playful animals and ball clearly establish the requested beach scene. Warm sky gradients and clean silhouettes make it appealing. Animal construction is underdeveloped: torso and limb connections are unclear, especially in the round-eared foreground figure. The dolphin lacks a convincing splash, and broad reflection bands suggest sunset light without resolving its behavior on water.
Muse Spark Open
A coherent sunset beach with readable activities, balanced framing and controlled colour transitions. Small accessories add interest, but schematic anatomy, limited surface detail, weak directional shadows and a geometric reflection constrain its finish. Most shapes and overlaps remain clean.
Score breakdown
| Category | GPT-5.5 | Muse Spark Open |
|---|---|---|
| Task & likeness | 7.0/10 | 8.0/10 |
| Anatomy & construction | 2.5/10 | 6.0/10 |
| Space & placement | 3.0/10 | 6.5/10 |
| Light & reflections | 3.0/10 | 5.5/10 |
| Purposeful detail | 3.0/10 | 6.5/10 |
| Artistry & character | 3.0/10 | 5.5/10 |
| Materials & effects | 3.0/10 | 6.0/10 |
| Visual integrity | 3.5/10 | 8.0/10 |
Benchmark task
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Ground Truth
Same task instructionsPhysical reasoning, light and visual reconstruction.
GPT-5.5 40.8/100 Rank 27/53

Muse Spark Open 51.9/100 Rank 12/53

The judgment
GPT-5.5
This benchmark has not been assessed yet.
Muse Spark Open
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 instructionsScene composition and interacting subjects.
GPT-5.5 35.8/100 Rank 45/53

Muse Spark Open 43.9/100 Rank 40/53

The judgment
GPT-5.5
The raccoon's masked face, bright hull and sweeping wake make the scene readable and lively. The dog is much less resolved: its head is ambiguous, overlapping brown forms obscure its anatomy, and its paws do not visibly grip the controls. Smooth shapes and cheerful colors provide appeal, but weak steering construction and limited depth keep the drawing uneven.
Muse Spark Open
Expressive faces, distinct accessories and clean color separation make the scene appealing and recognizable. Character detail is stronger than the functional construction: steering contact, limb overlaps and seating remain ambiguous. The readable hull and lively spray establish motion, while limited directional shading and simplified surfaces constrain depth and physical coherence.
Score breakdown
| Category | GPT-5.5 | Muse Spark Open |
|---|---|---|
| Task & likeness | 3.5/10 | 4.0/10 |
| Anatomy & construction | 3.0/10 | 3.0/10 |
| Space & placement | 4.5/10 | 6.0/10 |
| Light & reflections | 5.0/10 | 4.5/10 |
| Purposeful detail | 3.5/10 | 7.0/10 |
| Artistry & character | 3.0/10 | 3.5/10 |
| Materials & effects | 5.0/10 | 5.0/10 |
| Visual integrity | 3.0/10 | 5.0/10 |
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 instructionsSubject construction and spatial relationships.
GPT-5.5 60.0/100 Rank 36/53

Muse Spark Open 60.5/100 Rank 34/53

The judgment
GPT-5.5
The oversized bill, bright bicycle and sunset create an appealing, recognizable cartoon. Riding mechanics are less convincing: the wing has no clear steering contact, leg attachments are uneven, and feet do not visibly engage pedals. A dark notch complicates the rear neck junction. Clean contours and orderly spokes provide polish, while simplified anatomy and lighting limit depth.
Muse Spark Open
A controlled, appealing cartoon with a recognizable pelican, expressive face and clean curved forms. Feather lines, spokes and bill shading provide useful complexity. Aligned wheels and a ground shadow establish placement, but uncertain pedal contacts and obscured mechanical connections weaken support and riding action. Lighting remains loosely coordinated with the sun.
Score breakdown
| Category | GPT-5.5 | Muse Spark Open |
|---|---|---|
| Task & likeness | 7.5/10 | 7.5/10 |
| Anatomy & construction | 4.5/10 | 5.0/10 |
| Space & placement | 6.5/10 | 6.0/10 |
| Light & reflections | 6.5/10 | 5.0/10 |
| Purposeful detail | 5.5/10 | 6.5/10 |
| Artistry & character | 5.0/10 | 5.5/10 |
| Materials & effects | 6.0/10 | 6.0/10 |
| Visual integrity | 7.5/10 | 7.5/10 |
Benchmark task
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.