STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Qwen4-Max-Preview vs Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) leads Qwen4-Max-Preview by 3.8 points on StealthMark, 62.6 to 58.8. It leads on 5 of 9 benchmarks, including Foresight, and Qwen4-Max-Preview on 4, including Latch. Union Alpha scores higher on Ground Truth.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

58.8/100Overall rank 12/58
62.6/100Overall rank 8/58

General Intelligence

54.6/100
58.7/100

Visual Intelligence

66.3/100
69.6/100

Reasoning efficiency

How many reasoning tokens a model needs for the quality it delivers.

Single-step reasoning How much it reasons to understand a task

Multi-step reasoning How much it keeps reasoning as a task goes on

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

Cost efficiency

How much Performance you get for your money.

  • Qwen4-Max-PreviewNot measured

BENCHMARK BY BENCHMARK

Where each model leads

  • Qwen4-Max-Preview
  • Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
  • Other models
  • Median

DATASHEET

Specs and pricing

Qwen4-Max-Preview runs 2.6× faster in our speed test. Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) scores higher on StealthMark.

  • Qwen4-Max-Preview
  • Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
  • Other models
  • Median
Context windowTokens per request, max output below
Qwen4-Max-Preview: Not publishedPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM): 262K131K max output
Output speedTokens per second, our measurement
Qwen4-Max-Preview: 662.6× fastertokens/sPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM): 26tokens/s
Developer
Not publishedCircuit & Chisel / Unbiased
Released
Not published20 Sep 2026
Origin
Not publishedUnited States
Input → output
Not publishedText, image → text

Full datasheets, every price and sourcePareto 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.

Qwen4-Max-Preview 57.5/100Rank 14/54

Survived 1 of 3
Foresight: complete playing field
Level 310 ptsTurn 15 / 20

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 78.7/100Rank 1/54

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

Points per level

LevelQwen4-Max-PreviewPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Level 1Second Thoughts
20 ptsSurvived
27 ptsSurvived
Level 2Pressure Pot
12 ptsOut of lives
12 ptsOut of lives
Level 3Hide or Flight
10 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.

Qwen4-Max-Preview 67.3/100Rank 21/55

Cleared 5 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 36.5/100Rank 37/55

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

Points per level

LevelQwen4-Max-PreviewPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
8.8 ptsClearedFinished early · 1 beacon left
9.8 ptsCleared
Level 3Relay vault
19.2 ptsCleared
14.2 ptsClearedFinished early · 4 beacons left
Level 4Passing bay
17.2 ptsClearedFinished early · 3 beacons left
9.2 ptsFinished early
Level 5Second thoughts
20.6 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 8/58

Union Alpha: Newton's Mirror SVG benchmark

The judgment

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.

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

CategoryQwen4-Max-PreviewPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
State at 600 ms24.5/2524.0/25
Camera and placement14.0/1513.5/15
Reflections39.0/12034.5/120
Materials and scale6.5/1010.0/10
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 6/58

Union Alpha: Selfie SVG benchmark

The judgment

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.

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

CategoryQwen4-Max-PreviewPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness8.5/109.0/10
Anatomy & construction7.5/107.5/10
Space & placement7.5/108.5/10
Light & reflections7.0/107.5/10
Purposeful detail8.0/107.0/10
Artistry & character7.5/107.5/10
Materials & effects6.5/107.5/10
Visual integrity7.5/107.0/10

Benchmark task

Qwen4-Max-Preview

A floating capybara in ornate robes tests character anatomy, layered fabric and the placement of surrounding luminous forms.

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

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.

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

CategoryQwen4-Max-PreviewPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness4.5/106.5/10
Anatomy & construction5.5/105.0/10
Space & placement5.0/106.5/10
Light & reflections6.5/106.0/10
Purposeful detail6.0/105.5/10
Artistry & character5.5/106.5/10
Materials & effects5.0/105.0/10
Visual integrity5.5/107.0/10

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

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.

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

CategoryQwen4-Max-PreviewPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness8.5/109.0/10
Anatomy & construction8.0/107.0/10
Space & placement6.5/108.0/10
Light & reflections7.5/107.0/10
Purposeful detail8.0/107.0/10
Artistry & character8.5/106.0/10
Materials & effects6.5/106.5/10
Visual integrity7.0/107.0/10

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 9/58

Union Alpha: Ground Truth SVG benchmark

The judgment

Qwen4-Max-Preview

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

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.

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

CategoryQwen4-Max-PreviewPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness8.0/108.0/10
Anatomy & construction7.5/106.5/10
Space & placement6.0/107.5/10
Light & reflections6.5/105.5/10
Purposeful detail8.0/107.0/10
Artistry & character6.5/107.0/10
Materials & effects7.0/107.5/10
Visual integrity6.0/107.0/10

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

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.

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

CategoryQwen4-Max-PreviewPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness8.5/108.0/10
Anatomy & construction8.0/106.0/10
Space & placement7.5/107.0/10
Light & reflections6.5/106.0/10
Purposeful detail8.0/106.0/10
Artistry & character7.5/106.0/10
Materials & effects7.0/106.0/10
Visual integrity8.0/108.5/10

Benchmark task

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