Muse Spark 1.3 64.3/100Rank 7/54

STEALTHMARK · HEAD TO HEAD
All comparisons ↗Qwen4-Max-Preview leads Muse Spark 1.3 by 19.3 points on StealthMark, 58.8 to 39.5. It leads on 8 of 9 benchmarks, including Latch, and Muse Spark 1.3 on 1, including Foresight. Qwen4-Max-Preview scores higher on Newton's Mirror, with its largest category advantage in reflections.
See the difference ↘How many reasoning tokens a model needs for the quality it delivers.
How much Performance you get for your money.
BENCHMARK BY BENCHMARK
DATASHEET
Muse Spark 1.3 runs 4.9× faster in our speed test. Qwen4-Max-Preview scores higher on StealthMark.
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.


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.


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


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.
Qwen4-Max-Preview
The main placement, compact airborne black and contrasting cyan/crimson interaction states are largely supported. Recognizable first mirror images earn substantial local credit despite modest silhouette and overlap errors. Most of the defining mirror system remains missing, especially nested spherical imagery, outer chains and repeated emitter mapping. Crimson also extends slightly too far down the facing surface.
| Category | Muse Spark 1.3 | Qwen4-Max-Preview |
|---|---|---|
| State at 600 ms | 6.0/25 | 24.5/25 |
| Camera and placement | 8.5/15 | 14.0/15 |
| Reflections | 5.5/120 | 39.0/120 |
| Materials and scale | 4.0/10 | 6.5/10 |
| Floor-damage reward | 0.0/10 | 0.0/10 |
A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.
Visual construction and creative interpretation.


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.
Qwen4-Max-Preview
A coherent celestial character with readable costume layers, controlled ornament and coordinated luminous accents. Simplified joints, shallow frontal space and limited material modeling constrain construction and drawing complexity. The raised palm's orientation remains only partially demonstrated.
| Category | Muse Spark 1.3 | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 8.0/10 | 8.5/10 |
| Anatomy & construction | 5.0/10 | 7.5/10 |
| Space & placement | 6.5/10 | 7.5/10 |
| Light & reflections | 7.0/10 | 7.0/10 |
| Purposeful detail | 6.5/10 | 8.0/10 |
| Artistry & character | 5.5/10 | 7.5/10 |
| Materials & effects | 6.5/10 | 6.5/10 |
| Visual integrity | 7.5/10 | 7.5/10 |
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.
Qwen4-Max-Preview
A floating capybara in ornate robes tests character anatomy, layered fabric and the placement of surrounding luminous forms.
Precise visual recall and portrait reconstruction.


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.
Qwen4-Max-Preview
A coherent, recognizable interpretation with developed facial shading and purposeful portrait details. The frontal, nearly symmetric body, inflated sleeves and unresolved hand articulation substantially limit replication and construction. Layered scenery supplies basic depth, while uniformly smooth surfaces and schematic folds constrain material character and drawing complexity.
| Category | Muse Spark 1.3 | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 1.0/10 | 4.5/10 |
| Anatomy & construction | 1.5/10 | 5.5/10 |
| Space & placement | 1.5/10 | 5.0/10 |
| Light & reflections | 1.5/10 | 6.5/10 |
| Purposeful detail | 1.0/10 | 6.0/10 |
| Artistry & character | 1.5/10 | 5.5/10 |
| Materials & effects | 1.5/10 | 5.0/10 |
| Visual integrity | 3.0/10 | 5.5/10 |
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
Creativity, perspective and visual beauty.


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.
Qwen4-Max-Preview
A coherent sunset illustration with sweeping palms, recognizable wildlife and varied, readable beach details. Atmospheric layering and controlled contours strengthen its character. Basic animal anatomy, overhead-looking foreground creatures and schematic cast shadows limit construction and physical depth.
| Category | Muse Spark 1.3 | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 6.5/10 | 8.5/10 |
| Anatomy & construction | 3.0/10 | 8.0/10 |
| Space & placement | 5.5/10 | 6.5/10 |
| Light & reflections | 6.5/10 | 7.5/10 |
| Purposeful detail | 5.0/10 | 8.0/10 |
| Artistry & character | 3.5/10 | 8.5/10 |
| Materials & effects | 3.0/10 | 6.5/10 |
| Visual integrity | 3.5/10 | 7.0/10 |
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Physical reasoning, light and visual reconstruction.


Muse Spark 1.3
This benchmark has not been assessed yet.
Qwen4-Max-Preview
This benchmark has not been assessed yet.
A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.
Scene composition and interacting subjects.


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.
Qwen4-Max-Preview
An expressive cartoon with purposeful accessory detail, readable steering and directional spray. The aligned sunset reflection adds physical coherence. Simplified joints and the frontal raccoon's uncertain seated support continue to limit anatomy, perspective and integrity.
| Category | Muse Spark 1.3 | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 8.5/10 | 8.0/10 |
| Anatomy & construction | 6.0/10 | 7.5/10 |
| Space & placement | 7.0/10 | 6.0/10 |
| Light & reflections | 5.0/10 | 6.5/10 |
| Purposeful detail | 6.5/10 | 8.0/10 |
| Artistry & character | 5.0/10 | 6.5/10 |
| Materials & effects | 6.0/10 | 7.0/10 |
| Visual integrity | 6.0/10 | 6.0/10 |
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.
Subject construction and spatial relationships.


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.
Qwen4-Max-Preview
A detailed coastal illustration with readable seated support, steering and pedal contacts. Continuous anatomy, coherent bicycle construction and purposeful small features support its expressive composition. Simplified limb articulation, modest perspective depth and weakly directional ground shadows limit physical conviction.
| Category | Muse Spark 1.3 | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 8.5/10 | 8.5/10 |
| Anatomy & construction | 6.0/10 | 8.0/10 |
| Space & placement | 7.0/10 | 7.5/10 |
| Light & reflections | 6.0/10 | 6.5/10 |
| Purposeful detail | 7.0/10 | 8.0/10 |
| Artistry & character | 5.5/10 | 7.5/10 |
| Materials & effects | 6.5/10 | 7.0/10 |
| Visual integrity | 7.0/10 | 8.0/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.