STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Muse Spark Open vs Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) leads Muse Spark Open by 18.5 points on StealthMark, 62.6 to 44.1. It leads on 8 of 9 benchmarks, including Foresight, and Muse Spark Open on 1, including Latch. Union 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
62.6/100Overall rank 7/53

General Intelligence

42.6/100
58.7/100

Visual Intelligence

46.6/100
69.6/100

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
  • Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)Not measured

Open or local

BENCHMARK BY BENCHMARK

Where each model leads

  • Muse Spark Open
  • Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
  • Other models
  • Median

DATASHEET

Specs and pricing

Muse Spark Open takes 4× more context and runs 14× faster in our speed test. Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) scores higher on StealthMark.

  • Muse Spark Open
  • Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
  • Other models
  • Median
PricePer 1M output tokens, input below
Muse Spark Open: $4.25$1.25 inputPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM): No list price
Context windowTokens per request, max output below
Muse Spark Open: 1M4× larger1M max outputPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM): 262K131K max output
Output speedTokens per second, our measurement
Muse Spark Open: 36114× fastertokens/sPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM): 26tokens/s
SizeTotal and active parameters
Muse Spark Open: 816B42B activePareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM): Not disclosed
Developer
MetaCircuit & Chisel / Unbiased
Released
15 Oct 202620 Sep 2026
Origin
United StatesBoth
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.Not published

Full datasheets, every price and sourceMuse Spark Open ↗Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) ↗

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

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 78.7/100Rank 1/47

Survived 2 of 3
Foresight: complete playing field
Level 319 ptsTurn 20 / 20

Points per level

LevelMuse Spark OpenPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Level 1Second Thoughts
4 ptsOut of lives
27 ptsSurvived
Level 2Pressure Pot
9 ptsOut of lives
12 ptsOut of lives
Level 3Hide or Flight
8 ptsOut of lives
19 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

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 36.5/100Rank 30/48

Cleared 4 of 5
Latch: complete playing field
Level 519.4 ptsTurn 33 / 40

Points per level

LevelMuse Spark OpenPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
9.8 ptsCleared
Level 3Relay vault
19.2 ptsCleared
14.2 ptsClearedFinished early · 4 beacons left
Level 4Passing bay
17.8 ptsClearedFinished early · 1 beacon left
9.2 ptsFinished early
Level 5Second thoughts
19.6 ptsCleared
19.4 ptsCleared

Newton's Mirror

Same task instructions

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

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 52.0/100 Rank 7/53

Union Alpha: Newton's Mirror SVG benchmark

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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

Recognizable near-field sphere placement and bilateral convergence provide limited optical structure. Broad gray regions interrupt lateral sightlines and truncate side-floor images. Missing outer chains, absent nested sphere imagery and incomplete planar and curved emitter mappings dominate the reflection system.

Score breakdown

CategoryMuse Spark OpenPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
State at 600 ms14.0/2524.0/25
Camera and placement6.0/1513.5/15
Reflections8.0/12034.5/120
Materials and scale3.5/1010.0/10
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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 76.5/100 Rank 7/53

Union Alpha: Selfie SVG benchmark

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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

A strong futuristic emblem with clear hierarchy, controlled negative space and distinctive typography. Silver and gunmetal layers give the sweeping ribbons convincing graphic depth, while red accents remain restrained. Ambiguous concealed connections and occasionally abrupt highlight bands limit the construction and material realism.

Score breakdown

CategoryMuse Spark OpenPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness5.0/109.0/10
Anatomy & construction4.5/107.5/10
Space & placement6.0/108.5/10
Light & reflections5.0/107.5/10
Purposeful detail6.0/107.0/10
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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

An interwoven metallic emblem tests ribbon geometry, overlapping forms and the appearance of reflective metal against a dark background.

Mona Lisa

Different 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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

The centered portrait, folded hands, dark clothing and hazy landscape clearly evoke the Mona Lisa. Muted colors and soft facial shading create a coherent illustration, but replication remains schematic: the face is broad, eyes outlined, smile simplified and overlapping fingers poorly resolved. Angular landscape shapes and flat fabric limit depth and painterly richness.

Score breakdown

CategoryMuse Spark OpenPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness3.0/106.5/10
Anatomy & construction3.0/105.0/10
Space & placement5.0/106.5/10
Light & reflections4.5/106.0/10
Purposeful detail4.0/105.5/10
Artistry & character3.0/106.5/10
Materials & effects4.0/105.0/10
Visual integrity6.0/107.0/10

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

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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

A cohesive sunset palette, sweeping shoreline and playful animals make an appealing beach illustration. The sun’s reflection establishes a clear focal axis, balanced by the palm and umbrella. Clean silhouettes and small decorative features reward inspection, though simplified anatomy, repetitive reflection bars and generic oval shadows limit volume and naturalism.

Score breakdown

CategoryMuse Spark OpenPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness8.0/109.0/10
Anatomy & construction6.0/107.0/10
Space & placement6.5/108.0/10
Light & reflections5.5/107.0/10
Purposeful detail6.5/107.0/10
Artistry & character5.5/106.0/10
Materials & effects6.0/106.5/10
Visual integrity8.0/107.0/10

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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 63.3/100 Rank 8/53

Union Alpha: Ground Truth SVG benchmark

The judgment

Muse Spark Open

This benchmark has not been assessed yet.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

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

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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

Expressive animals, a readable riding arrangement and sweeping spray create an appealing cartoon. The raccoon sits convincingly on the dog's back, but the dog's paw does not clearly grip the handlebar, whose connection to the hull is unresolved. Flat lighting provides little volume or reflection. A dark rectangular strip interrupts the upper-right background.

Score breakdown

CategoryMuse Spark OpenPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness4.0/108.0/10
Anatomy & construction3.0/106.5/10
Space & placement6.0/107.5/10
Light & reflections4.5/105.5/10
Purposeful detail7.0/107.0/10
Artistry & character3.5/107.0/10
Materials & effects5.0/107.5/10
Visual integrity5.0/107.0/10

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.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

The pelican is immediately recognizable, with an expressive face, convincing bill silhouette and appealing pastel composition. Both legs connect to feet, and the wing reaches the handlebar. Bicycle construction is less resolved: the far pedal lacks a clear crank connection and no chain is visible. Clean contours and orderly spokes support the illustration, while flat lighting and simplified surfaces limit depth.

Score breakdown

CategoryMuse Spark OpenPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness7.5/108.0/10
Anatomy & construction5.0/106.0/10
Space & placement6.0/107.0/10
Light & reflections5.0/106.0/10
Purposeful detail6.5/106.0/10
Artistry & character5.5/106.0/10
Materials & effects6.0/106.0/10
Visual integrity7.5/108.5/10

Benchmark task

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