Muse Ember (early version) 32.3/100Rank 31/54

STEALTHMARK · HEAD TO HEAD
All comparisons ↗Qwen4-Max-Preview leads Muse Ember (early version) by 10.8 points on StealthMark, 58.8 to 48.0. It leads on 8 of 9 benchmarks, including both games, and Muse Ember (early version) on 1. 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 Ember (early version) runs 2.7× faster in our speed test. Qwen4-Max-Preview scores higher on StealthMark.
Full datasheets, every price and sourceMuse Ember (early version) ↗
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 Ember (early version)
The artwork establishes approximate central placement, a separate airborne black blob, and basic wall and floor sphere images. Its defining weaknesses are the largely absent recursive reflection system, missing emitter mappings, satin steel appearance and unresolved paint interaction. The black lateral wedges do not establish a separate viewport, and the hidden floor contact does not establish a gap. The category values remain unchanged.
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 Ember (early version) | Qwen4-Max-Preview |
|---|---|---|
| State at 600 ms | 19.0/25 | 24.5/25 |
| Camera and placement | 11.0/15 | 14.0/15 |
| Reflections | 21.5/120 | 39.0/120 |
| Materials and scale | 6.0/10 | 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 Ember (early version)
A cheerful, readable cartoon captures the crouton's signature expression and many specific accessories. Coherent cube geometry and foreground foreshortening support the selfie. Simple construction and flat material treatment limit its sophistication, while the tipping raft, advancing soup and unnoticed soaking remain insufficiently clear.
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 Ember (early version) | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 6.5/10 | 8.5/10 |
| Anatomy & construction | 5.5/10 | 7.5/10 |
| Space & placement | 6.5/10 | 7.5/10 |
| Light & reflections | 5.5/10 | 7.0/10 |
| Purposeful detail | 7.0/10 | 8.0/10 |
| Artistry & character | 5.0/10 | 7.5/10 |
| Materials & effects | 5.5/10 | 6.5/10 |
| Visual integrity | 7.5/10 | 7.5/10 |
Muse Ember (early version)
Character scenes test expression, anatomy, materials and coherent visual construction.
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 Ember (early version)
A recognizable, coherent simplification with readable eyes, a restrained smile and modest facial volume. Frontal symmetry, an oversized head, capsule-like hands and geometric scenery substantially limit likeness, anatomy and depth. Clean contours preserve basic integrity but do not establish sophisticated construction or finish.
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 Ember (early version) | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 4.5/10 | 4.5/10 |
| Anatomy & construction | 4.0/10 | 5.5/10 |
| Space & placement | 4.5/10 | 5.0/10 |
| Light & reflections | 5.0/10 | 6.5/10 |
| Purposeful detail | 4.0/10 | 6.0/10 |
| Artistry & character | 4.5/10 | 5.5/10 |
| Materials & effects | 4.0/10 | 5.0/10 |
| Visual integrity | 6.0/10 | 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 Ember (early version)
A colorful, readable sunset beach scene with playful subjects and a clear central reflection. Purposeful equipment and animal details reward inspection, and the principal attachments remain intact. Basic geometric anatomy, mixed viewpoints and sparse directional shadows limit its construction and depth; smooth gradients provide atmosphere with little material differentiation.
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 Ember (early version) | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 8.5/10 | 8.5/10 |
| Anatomy & construction | 5.0/10 | 8.0/10 |
| Space & placement | 5.5/10 | 6.5/10 |
| Light & reflections | 5.5/10 | 7.5/10 |
| Purposeful detail | 7.0/10 | 8.0/10 |
| Artistry & character | 5.0/10 | 8.5/10 |
| Materials & effects | 5.5/10 | 6.5/10 |
| Visual integrity | 7.0/10 | 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 Ember (early version)
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 Ember (early version)
A readable cartoon with expressive faces, purposeful markings and clear water motion. Hull shading and an underside shadow establish modest depth. The dog contacts the controls, but the raccoon's frontal pose leaves its seated weight unresolved. Simple anatomy and limited shared perspective constrain the drawing.
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 Ember (early version) | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 7.0/10 | 8.0/10 |
| Anatomy & construction | 5.0/10 | 7.5/10 |
| Space & placement | 6.0/10 | 6.0/10 |
| Light & reflections | 6.0/10 | 6.5/10 |
| Purposeful detail | 6.5/10 | 8.0/10 |
| Artistry & character | 5.0/10 | 6.5/10 |
| Materials & effects | 5.5/10 | 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 Ember (early version)
A recognizable, expressive pelican cyclist with purposeful feather and bicycle detail. Readable steering reach, connected machinery and modest body shading earn additional credit. Jointless legs, uncertain pedal engagement and unclear seated support keep the central action only partially resolved; shallow space and simple materials further limit the illustration.
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 Ember (early version) | Qwen4-Max-Preview |
|---|---|---|
| Task & likeness | 7.0/10 | 8.5/10 |
| Anatomy & construction | 5.0/10 | 8.0/10 |
| Space & placement | 5.5/10 | 7.5/10 |
| Light & reflections | 5.5/10 | 6.5/10 |
| Purposeful detail | 6.5/10 | 8.0/10 |
| Artistry & character | 5.5/10 | 7.5/10 |
| Materials & effects | 5.0/10 | 7.0/10 |
| Visual integrity | 6.0/10 | 8.0/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.