STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Qwen3.6-35B-A3B vs Step 5 Preview

Step 5 Preview leads Qwen3.6-35B-A3B by 18.2 points on StealthMark, 39.0 to 20.8. Qwen3.6-35B-A3B leads on 5 of 9 benchmarks, including Foresight, and Step 5 Preview on 4, including Latch. Step 5 Preview scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

20.8/100Overall rank 46/53
39.0/100Overall rank 36/53

General Intelligence

12.7/100
37.1/100

Visual Intelligence

34.0/100
41.9/100

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

Open or local

Local modelOpen model · Apache-2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Qwen3.6-35B-A3B
  • Step 5 Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1.01M tokens of context.

  • Qwen3.6-35B-A3B
  • Step 5 Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
Qwen3.6-35B-A3B: $1.49$0.25 inputStep 5 Preview: No list price
Context windowTokens per request, max output below
Qwen3.6-35B-A3B: 1.01MTied64K max outputStep 5 Preview: 1MTied
Output speedTokens per second, our measurement
Qwen3.6-35B-A3B: 577tokens/sStep 5 Preview: Not measured
SizeTotal and active parameters
Qwen3.6-35B-A3B: 35B3B activeStep 5 Preview: 600B27B active
Developer
QwenStepFun
Released
16 Apr 2026Not published
Origin
ChinaNot published
Input → output
Text, image, video → textBoth
Architecture
MoE causal language model with vision encoder; Gated DeltaNet + gated attention; 256 experts, 8 routed + 1 shared activeSparse mixture-of-experts; 92 layers (88 MoE), 352 routed experts with 8 selected per token plus a shared expert; grouped-query attention with 512-token sliding windows and full attention every fourth layer; 3 multi-token-prediction layers; vision tower for image and video input

Full datasheets, every price and sourceQwen3.6-35B-A3B ↗Step 5 Preview ↗

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.

Qwen3.6-35B-A3B 20.7/100Rank 41/49

Survived 1 of 3
Foresight: complete playing field
Level 39 ptsTurn 20 / 20

Step 5 Preview 59.9/100Rank 42/491 of 3 levels

1 of 3 played
Foresight: complete playing field
Level 122 ptsTurn 28 / 28

Points per level

LevelQwen3.6-35B-A3BStep 5 Preview
Level 1Second Thoughts
4 ptsOut of lives
22 ptsSurvived
Level 2Pressure Pot
3 ptsOut of lives
Pending
Level 3Hide or Flight
9 ptsSurvived
Pending

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.

Qwen3.6-35B-A3B 3.6/100Rank 46/50

Cleared 1 of 5
Latch: complete playing field
Level 57.8 ptsTurn 36 / 40

Step 5 Preview 40.7/100Rank 28/50

Cleared 4 of 5
Latch: complete playing field
Level 515 ptsTurn 35 / 40

Points per level

LevelQwen3.6-35B-A3BStep 5 Preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
1 ptsOut of turns
9 ptsCleared
Level 3Relay vault
0.2 ptsFinished early
18.6 ptsCleared
Level 4Passing bay
3 ptsOut of turns
15.6 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
7.8 ptsFinished early
15 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

Qwen3.6-35B-A3B

The artwork demonstrates rounded volume, recognizable paint colors and a compact black feature at an appropriate screen height. The enlarged main-sphere framing, unsupported crimson and cyan interaction histories, oversized compact paint balls and largely missing mirror structure remain substantial weaknesses. The core assessment is 20/170; with no demonstrated floor damage, the combined assessment remains 20/180.

Step 5 Preview

The main sphere, airborne black and small colored features occupy broadly appropriate positions. Most of the defining mirror system is absent, and paint interaction remains only partially supported. The small paint features do not visibly establish a separate volume-scale violation.

Score breakdown

CategoryQwen3.6-35B-A3BStep 5 Preview
State at 600 ms2.5/2520.0/25
Camera and placement4.0/1513.5/15
Reflections3.5/12020.0/120
Materials and scale2.5/107.0/10
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.

The judgment

Qwen3.6-35B-A3B

An appealing fantasy illustration with coordinated ornament, readable suspension and luminous turquoise accents. Plausible limb attachments and soft shading support competent execution. Bear-like proportions, unclear paw gestures, insufficient white robe fabric, crowded chest details and shallow material modeling limit its finish.

Step 5 Preview

A charming diagonal climber and warm palette communicate the central idea. Simple rounded construction, crowded limb counting, uncertain footholds and an unattached upper shelf limit its physical coherence. Growth bands and the yarn trail add specificity, but the requested material distinctions and unravelled bootie remain underdeveloped.

Score breakdown

CategoryQwen3.6-35B-A3BStep 5 Preview
Task & likeness6.0/106.0/10
Anatomy & construction6.0/104.5/10
Space & placement6.5/105.0/10
Light & reflections7.0/105.5/10
Purposeful detail6.5/105.5/10
Artistry & character6.0/105.0/10
Materials & effects5.5/106.0/10
Visual integrity7.5/105.0/10

Benchmark task

Qwen3.6-35B-A3B

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

Step 5 Preview

Character scenes test expression, anatomy, materials and coherent visual construction.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Qwen3.6-35B-A3B

A recognizable but basic geometric interpretation. Muted colors and soft shading provide cohesion, while weak likeness, unresolved hands, rigid anatomy and shallow landscape construction substantially limit the replication.

Step 5 Preview

A recognizable, coherent simplification with purposeful facial contours and differentiated fingers. These provide more construction and detail than the broad silhouette alone suggests. The oversized face, frontal seated pose, unresolved wrists and sparse landscape still substantially limit likeness, depth and finish.

Score breakdown

CategoryQwen3.6-35B-A3BStep 5 Preview
Task & likeness2.0/104.0/10
Anatomy & construction1.0/104.0/10
Space & placement2.0/104.0/10
Light & reflections0.5/103.5/10
Purposeful detail1.5/104.0/10
Artistry & character1.5/104.0/10
Materials & effects1.5/103.0/10
Visual integrity2.0/103.5/10

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

Qwen3.6-35B-A3B

A recognizable beach sunset with balanced framing and appealing color transitions. Birds, boats and small animals fulfill the main scene requirements. Elementary anatomy, faint details, weak grounding and rigid reflection columns limit depth and finish.

Step 5 Preview

A recognizable sunset beach with clear warm-cool contrast and playful accessories. Basic animal construction, shallow foreground placement and schematic reflections limit spatial and physical credibility. Sparse descriptive detail and abruptly ended sky bands constrain the finish.

Score breakdown

CategoryQwen3.6-35B-A3BStep 5 Preview
Task & likeness7.5/104.0/10
Anatomy & construction4.5/103.0/10
Space & placement5.5/103.5/10
Light & reflections4.5/103.5/10
Purposeful detail4.5/103.0/10
Artistry & character4.5/103.0/10
Materials & effects5.5/103.5/10
Visual integrity5.0/104.0/10

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

Qwen3.6-35B-A3B

This benchmark has not been assessed yet.

Step 5 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

Qwen3.6-35B-A3B

Clean shapes, cheerful faces and bright colors make the riding arrangement readable. The dog does not visibly operate the control, while awkward limbs, shallow hull placement and stiff poses limit credibility. Gradients and layered foam add modest volume and motion. The obscured tail attachment does not establish detachment.

Step 5 Preview

Recognizable animals, a bright palette and identifying accessories support a basic cartoon. Primitive anatomy, partial seated support, unresolved steering and weak hull-water contact limit the central action. Lighting and spray provide atmosphere without establishing convincing physical depth.

Score breakdown

CategoryQwen3.6-35B-A3BStep 5 Preview
Task & likeness4.5/104.0/10
Anatomy & construction3.5/104.5/10
Space & placement5.5/103.0/10
Light & reflections3.5/103.5/10
Purposeful detail4.5/104.0/10
Artistry & character4.0/103.5/10
Materials & effects4.0/103.0/10
Visual integrity3.5/103.0/10

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

Qwen3.6-35B-A3B

A cheerful, readable illustration with a distinctive pelican silhouette, clean contours and an orderly landscape. Soft glow and restrained shading provide modest atmosphere. Construction is weaker: the handlebar is disconnected, wings do not reach the controls, and overlapping legs leave pedaling ambiguous. Simple forms and mostly flat materials limit depth and drawing sophistication.

Step 5 Preview

The pelican and bicycle are recognizable, with a pleasant palette and basic diffuse shading. The riding relationship fails physically: the bird is unsupported, the front wheel is unmounted, and pedalling is unresolved. Simple geometric construction and sparse material treatment further limit the drawing.

Score breakdown

CategoryQwen3.6-35B-A3BStep 5 Preview
Task & likeness7.0/103.0/10
Anatomy & construction3.5/103.0/10
Space & placement6.0/103.0/10
Light & reflections5.5/103.0/10
Purposeful detail7.0/104.0/10
Artistry & character5.0/103.0/10
Materials & effects5.5/103.0/10
Visual integrity4.5/102.0/10

Benchmark task

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