STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Muse Spark Open vs GLM-5.3-Flash

GLM-5.3-Flash leads Muse Spark Open by 4.7 points on StealthMark, 48.8 to 44.1. It leads on 8 of 9 benchmarks, including Foresight, and Muse Spark Open on 1, including Latch. Ox Alpha scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

44.1/100Overall rank 29/53
48.8/100Overall rank 19/53

General Intelligence

42.6/100
42.2/100

Visual Intelligence

46.6/100
59.4/100

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

  • Muse Spark Open

Open or local

Local modelOpen model · MIT

BENCHMARK BY BENCHMARK

Where each model leads

  • Muse Spark Open
  • GLM-5.3-Flash
  • Other models
  • Median

DATASHEET

Specs and pricing

Muse Spark Open runs 4.1× faster in our speed test. GLM-5.3-Flash scores higher on StealthMark and is 8.5× cheaper per output token. Both take about 1M tokens of context.

  • Muse Spark Open
  • GLM-5.3-Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
Muse Spark Open: $4.25$1.25 inputGLM-5.3-Flash: $0.508.5× cheaper$0.15 input
Context windowTokens per request, max output below
Muse Spark Open: 1MTied1M max outputGLM-5.3-Flash: 1MTied131K max output
Output speedTokens per second, our measurement
Muse Spark Open: 3614.1× fastertokens/sGLM-5.3-Flash: 89tokens/s
SizeTotal and active parameters
Muse Spark Open: 816B42B activeGLM-5.3-Flash: 320B18B active
Developer
MetaZ.AI
Released
15 Oct 202626 Aug 2026
Origin
United StatesNot published
Input → output
Text, image, audio, video → textText, image → text
Architecture
Sparse 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.Hybrid sparse and linear attention MoE

Full datasheets, every price and sourceMuse Spark Open ↗GLM-5.3-Flash ↗

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.

Muse Spark Open 29.4/100Rank 34/47

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 15 / 20

GLM-5.3-Flash 49.0/100Rank 27/472 of 3 levels

2 of 3 played
Foresight: complete playing field
Level 316 ptsTurn 20 / 20

Points per level

LevelMuse Spark OpenGLM-5.3-Flash
Level 1Second Thoughts
4 ptsOut of lives
9 ptsOut of lives
Level 2Pressure Pot
9 ptsOut of lives
Pending
Level 3Hide or Flight
8 ptsOut of lives
16 ptsSurvived

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.

Muse Spark Open 75.7/100Rank 12/48

Cleared 5 of 5
Latch: complete playing field
Level 519.6 ptsTurn 32 / 40

GLM-5.3-Flash 4.0/100Rank 48/483 of 5 levels

3 of 5 played
Latch: complete playing field
Level 30.6 ptsTurn 33 / 36

Points per level

LevelMuse Spark OpenGLM-5.3-Flash
Level 1Hold the door
5.2 ptsCleared
4.4 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
5.2 ptsFinished early
Level 3Relay vault
19.2 ptsCleared
0.6 ptsFinished early
Level 4Passing bay
17.8 ptsClearedFinished early · 1 beacon left
Pending
Level 5Second thoughts
19.6 ptsCleared
Not played

Newton's Mirror

Same task instructions

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

The judgment

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.

GLM-5.3-Flash

The setup is recognizable, but the paint interaction remains poorly established and off-center. The first wall and floor images provide coherent placement, scale, silhouette and occlusion cues, with faint lower echoes. Missing receding chains, nested imagery and ordered emitter mappings leave the reflection system heavily simplified. Dull shading does not convincingly depict polished steel or mirrors.

Score breakdown

CategoryMuse Spark OpenGLM-5.3-Flash
State at 600 ms14.0/2514.0/25
Camera and placement6.0/159.0/15
Reflections8.0/12021.5/120
Materials and scale3.5/103.5/10
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

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.

GLM-5.3-Flash

The expressive emerald face, ivory horns, gold accents and fine veining closely match the brief. Rounded volumes and layered shading create an appealing mascot. Rear hoof placement is cramped, lighting is somewhat inconsistent, and conspicuous white patches behind the muzzle interrupt the finish. Surfaces remain visibly stylized rather than photographic.

Score breakdown

CategoryMuse Spark OpenGLM-5.3-Flash
Task & likeness5.0/108.5/10
Anatomy & construction4.5/107.5/10
Space & placement6.0/107.5/10
Light & reflections5.0/108.0/10
Purposeful detail6.0/107.5/10
Artistry & character5.0/107.5/10
Materials & effects5.0/107.5/10
Visual integrity6.5/107.0/10

Benchmark task

Muse Spark Open

A small elephant protecting a delicate seed tests expressive anatomy, physical contact and contrasting organic materials.

GLM-5.3-Flash

A rounded jade bull raising a hoof tests anatomy, balance and the appearance of polished stone and metal.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

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.

GLM-5.3-Flash

The crossed arms, green dress and hazy landscape clearly evoke Mona Lisa. Replication is limited by the frontal pose, oversized eyes, elongated face and pronounced lips. Overlapping finger strips lack convincing knuckles and palm volume. The balanced framing and soft shading provide cohesion, but simplified anatomy, repetitive folds and blurred scenery keep the portrait basic.

Score breakdown

CategoryMuse Spark OpenGLM-5.3-Flash
Task & likeness3.0/104.5/10
Anatomy & construction3.0/104.5/10
Space & placement5.0/106.0/10
Light & reflections4.5/106.0/10
Purposeful detail4.0/105.0/10
Artistry & character3.0/105.0/10
Materials & effects4.0/105.5/10
Visual integrity6.0/104.0/10

Benchmark task

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

Beach

Same task instructions

Creativity, perspective and visual beauty.

The judgment

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.

GLM-5.3-Flash

Framing palms, a vivid sunset palette and balanced kite and umbrella create an appealing beach illustration. Layered water and shoreline give the scene depth, while aligned reflections reinforce the sunset. Small accessories add character and reward inspection. Figures and animals remain schematic, some overlaps are difficult to read, and simplified shadows and flat surfaces limit physical richness.

Score breakdown

CategoryMuse Spark OpenGLM-5.3-Flash
Task & likeness8.0/108.0/10
Anatomy & construction6.0/107.0/10
Space & placement6.5/108.0/10
Light & reflections5.5/108.0/10
Purposeful detail6.5/108.0/10
Artistry & character5.5/108.5/10
Materials & effects6.0/106.5/10
Visual integrity8.0/108.0/10

Benchmark task

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

Ground Truth

Same task instructions

Physical reasoning, light and visual reconstruction.

The judgment

Muse Spark Open

This benchmark has not been assessed yet.

GLM-5.3-Flash

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

Same task instructions

Scene composition and interacting subjects.

The judgment

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.

GLM-5.3-Flash

Recognizable animals, a supported riding pose and an energetic diagonal composition make the scene readable. Character details and spray strengthen its appeal. Simple limb construction, limited directional lighting and an unresolved steering connection constrain the drawing's physical precision and complexity.

Score breakdown

CategoryMuse Spark OpenGLM-5.3-Flash
Task & likeness4.0/107.0/10
Anatomy & construction3.0/105.0/10
Space & placement6.0/106.0/10
Light & reflections4.5/105.0/10
Purposeful detail7.0/106.5/10
Artistry & character3.5/104.0/10
Materials & effects5.0/106.0/10
Visual integrity5.0/106.0/10

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 instructions

Subject construction and spatial relationships.

The judgment

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.

GLM-5.3-Flash

The pelican, bicycle and seaside setting form a clear, appealing illustration. Circular wheels, readable frame tubes and clean silhouettes support the action. The legs connect to the body, but the far foot's pedal contact and wing-to-handlebar junction are cramped. Simple shading, uniform wave marks and limited surface texture keep the rendering relatively flat.

Score breakdown

CategoryMuse Spark OpenGLM-5.3-Flash
Task & likeness7.5/108.5/10
Anatomy & construction5.0/107.5/10
Space & placement6.0/107.5/10
Light & reflections5.0/106.5/10
Purposeful detail6.5/107.0/10
Artistry & character5.5/108.0/10
Materials & effects6.0/106.5/10
Visual integrity7.5/108.0/10

Benchmark task

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