STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Qwen3.5-9B vs Qwen4-Max-Preview

Qwen4-Max-Preview leads Qwen3.5-9B by 48.0 points on StealthMark, 58.8 to 10.8. It leads on all 9 benchmarks. Qwen4-Max-Preview scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

10.8/100Overall rank 58/58
58.8/100Overall rank 12/58

General Intelligence

7.9/100
54.6/100

Visual Intelligence

15.5/100
66.3/100

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

Cost efficiency

How much Performance you get for your money.

  • Qwen4-Max-PreviewNot measured

Open or local

Local modelOpen model · Apache-2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Qwen3.5-9B
  • Qwen4-Max-Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Qwen3.5-9B runs 2.4× faster in our speed test. Qwen4-Max-Preview scores higher on StealthMark.

  • Qwen3.5-9B
  • Qwen4-Max-Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
Qwen3.5-9B: $0.25$0.17 inputQwen4-Max-Preview: No list price
Context windowTokens per request, max output below
Qwen3.5-9B: 1.01MQwen4-Max-Preview: Not published
Output speedTokens per second, our measurement
Qwen3.5-9B: 1612.4× fastertokens/sQwen4-Max-Preview: 66tokens/s
SizeTotal and active parameters
Qwen3.5-9B: 9BAll activeEstimatedQwen4-Max-Preview: Not disclosed
Developer
QwenNot published
Released
2 Mar 2026Not published
Origin
ChinaNot published
Input → output
Text, image, video → textNot published
Architecture
Dense causal language model with vision encoder; Gated DeltaNet + gated attention; MTP-trainedNot published

Full datasheets, every price and sourceQwen3.5-9B ↗

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.

Qwen3.5-9B 12.8/100Rank 50/54

Survived 0 of 3
Foresight: complete playing field
Level 32 ptsTurn 8 / 20

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

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

Points per level

LevelQwen3.5-9BQwen4-Max-Preview
Level 1Second Thoughts
4 ptsOut of lives
20 ptsSurvived
Level 2Pressure Pot
4 ptsOut of lives
12 ptsOut of lives
Level 3Hide or Flight
2 ptsOut of lives
10 ptsOut of lives

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.

Qwen3.5-9B 3.8/100Rank 50/55

Cleared 1 of 5
Latch: complete playing field
Level 54.4 ptsTurn 33 / 40

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

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

Points per level

LevelQwen3.5-9BQwen4-Max-Preview
Level 1Hold the door
5 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
3.8 ptsFinished early
8.8 ptsClearedFinished early · 1 beacon left
Level 3Relay vault
1.2 ptsFinished early
19.2 ptsCleared
Level 4Passing bay
0.2 ptsFinished early
17.2 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
4.4 ptsFinished early
20.6 ptsCleared

Newton's Mirror

Same task instructions

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

The judgment

Qwen3.5-9B

Horizontal centering and a separate airborne black blob are visible. Cyan's recent contact and crimson's forward transport are insufficiently demonstrated, while sphere support remains obscured. The enlarged, lowered sphere substantially changes the composition. The wall and floor sphere images, recursive room structure and curved emitter mappings are almost entirely missing.

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.

Score breakdown

CategoryQwen3.5-9BQwen4-Max-Preview
State at 600 ms3.0/2524.5/25
Camera and placement4.5/1514.0/15
Reflections2.0/12039.0/120
Materials and scale3.0/106.5/10
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

Same task instructions

Visual construction and creative interpretation.

The judgment

Qwen3.5-9B

Glowing teal spheres and a harmonious palette provide visible strengths, but the central character remains seriously unresolved. A large gap separates head and torso, limbs cannot be traced, and scattered garment shapes fail to establish the ornate costume. The foreground mound replaces the tall enclosing arch. Clean primitive edges do not repair these construction failures.

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.

Score breakdown

CategoryQwen3.5-9BQwen4-Max-Preview
Task & likeness2.5/108.5/10
Anatomy & construction2.0/107.5/10
Space & placement3.0/107.5/10
Light & reflections3.5/107.0/10
Purposeful detail2.0/108.0/10
Artistry & character2.0/107.5/10
Materials & effects4.0/106.5/10
Visual integrity3.0/107.5/10

Benchmark task

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

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Qwen3.5-9B

A centered dark oval with sparse facial marks forms a simple graphic face, but scarcely replicates the Mona Lisa. The portrait's body, crossed hands, clothing and landscape are missing, while angular facial construction and flat tones lose its likeness, volume and subtle expression.

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.

Score breakdown

CategoryQwen3.5-9BQwen4-Max-Preview
Task & likeness0.0/104.5/10
Anatomy & construction0.5/105.5/10
Space & placement0.0/105.0/10
Light & reflections0.0/106.5/10
Purposeful detail0.5/106.0/10
Artistry & character1.0/105.5/10
Materials & effects0.0/105.0/10
Visual integrity0.5/105.5/10

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

Qwen3.5-9B

The beach is recognizable, and sweeping shoreline curves provide basic rhythm. Wildlife and playful activity remain poorly resolved, with ambiguous body construction and object contact. The sun glows without corresponding reflections or surface lighting. Fragmented subjects and an unintegrated rectangular panel substantially weaken composition and finish.

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.

Score breakdown

CategoryQwen3.5-9BQwen4-Max-Preview
Task & likeness1.5/108.5/10
Anatomy & construction0.5/108.0/10
Space & placement1.5/106.5/10
Light & reflections1.0/107.5/10
Purposeful detail2.5/108.0/10
Artistry & character1.5/108.5/10
Materials & effects0.5/106.5/10
Visual integrity1.5/107.0/10

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.

The judgment

Qwen3.5-9B

This benchmark has not been assessed yet.

Qwen4-Max-Preview

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

Qwen3.5-9B

Bright colors, clean individual shapes and basic animal cues make the scene partly recognizable. Back seating, body continuity, steering and jet ski construction remain unresolved. Background gradients and wave rhythm provide some finish, but substantial anatomical, spatial and interaction weaknesses dominate.

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.

Score breakdown

CategoryQwen3.5-9BQwen4-Max-Preview
Task & likeness2.5/108.0/10
Anatomy & construction1.0/107.5/10
Space & placement2.0/106.0/10
Light & reflections1.0/106.5/10
Purposeful detail1.5/108.0/10
Artistry & character1.0/106.5/10
Materials & effects1.0/107.0/10
Visual integrity2.5/106.0/10

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

Same task instructions

Subject construction and spatial relationships.

The judgment

Qwen3.5-9B

The oversized bill and orderly spoked wheels make the subject partly recognizable. Clean contours and strong color contrast provide graphic clarity, but unresolved appendages, steering, drivetrain and support dominate the construction. Sparse shading and detail 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.

Score breakdown

CategoryQwen3.5-9BQwen4-Max-Preview
Task & likeness4.0/108.5/10
Anatomy & construction1.5/108.0/10
Space & placement3.0/107.5/10
Light & reflections1.5/106.5/10
Purposeful detail2.5/108.0/10
Artistry & character1.5/107.5/10
Materials & effects1.5/107.0/10
Visual integrity2.5/108.0/10

Benchmark task

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