STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Qwen3.6-27B vs Step 5 Preview

Step 5 Preview leads Qwen3.6-27B by 6.6 points on StealthMark, 39.0 to 32.4. Qwen3.6-27B 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

32.4/100Overall rank 41/53
39.0/100Overall rank 36/53

General Intelligence

25.6/100
37.1/100

Visual Intelligence

43.9/100
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

  • Qwen3.6-27B
  • Step 5 Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1.01M tokens of context.

  • Qwen3.6-27B
  • Step 5 Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
Qwen3.6-27B: $3.60$0.60 inputStep 5 Preview: No list price
Context windowTokens per request, max output below
Qwen3.6-27B: 1.01MTied64K max outputStep 5 Preview: 1MTied
Output speedTokens per second, our measurement
Qwen3.6-27B: 96tokens/sStep 5 Preview: Not measured
SizeTotal and active parameters
Qwen3.6-27B: 27BAll activeStep 5 Preview: 600B27B active
Developer
Qwen / AlibabaStepFun
Released
22 Apr 2026Not published
Origin
ChinaNot published
Input → output
Text, image, video → textBoth
Architecture
Dense causal language model with vision encoder; hybrid Gated DeltaNet and gated attention; MTP-trainedSparse 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 sourceQwen3.6-27B ↗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.

Qwen3.6-27B 37.8/100Rank 24/49

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

LevelQwen3.6-27BStep 5 Preview
Level 1Second Thoughts
9 ptsOut of lives
22 ptsSurvived
Level 2Pressure Pot
6 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.

Qwen3.6-27B 28.5/100Rank 37/50

Cleared 3 of 5
Latch: complete playing field
Level 511 ptsTurn 25 / 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

LevelQwen3.6-27BStep 5 Preview
Level 1Hold the door
4.8 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
8.8 ptsClearedFinished early · 1 beacon left
9 ptsCleared
Level 3Relay vault
16.4 ptsClearedFinished early · 3 beacons left
18.6 ptsCleared
Level 4Passing bay
13.4 ptsFinished early
15.6 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
11 ptsFinished early
15 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

Qwen3.6-27B

The artwork depicts a shaded sphere, distinct paint colors and a separate airborne black blob. Crimson's apex overlap does not establish its earlier interaction and transport, while cyan's recent contact remains unsupported. Horizontal centering supplies limited camera agreement, but the sphere, black blob and prominent panel have substantial placement or projection departures. A few planar echoes provide reflection evidence; isolated patches and gradients replace most of the required mirror structure.

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

CategoryQwen3.6-27BStep 5 Preview
State at 600 ms5.0/2520.0/25
Camera and placement5.0/1513.5/15
Reflections8.0/12020.0/120
Materials and scale4.0/107.0/10
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

Qwen3.6-27B

An appealing decorative illustration with coordinated ornament, flowing panels and three glowing orbital lights. The arm arrangement reverses the requested sides. Uncertain neck continuity, concealed leg articulation, simplified paws, crowded chest jewelry and shallow surface modeling limit pose clarity and 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

CategoryQwen3.6-27BStep 5 Preview
Task & likeness6.5/106.0/10
Anatomy & construction5.0/104.5/10
Space & placement6.5/105.0/10
Light & reflections5.5/105.5/10
Purposeful detail6.0/105.5/10
Artistry & character5.0/105.0/10
Materials & effects5.0/106.0/10
Visual integrity7.0/105.0/10

Benchmark task

Qwen3.6-27B

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

Qwen3.6-27B

The portrait loosely evokes Mona Lisa through its palette and silhouette. Readable pupils, brows and lips provide limited detail, and the torso remains continuous. The frontal elongated face, unresolved chest-level limb forms, shallow landscape and pervasive blur substantially weaken likeness, anatomy and finish.

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

CategoryQwen3.6-27BStep 5 Preview
Task & likeness2.5/104.0/10
Anatomy & construction3.0/104.0/10
Space & placement4.0/104.0/10
Light & reflections4.0/103.5/10
Purposeful detail2.5/104.0/10
Artistry & character2.5/104.0/10
Materials & effects3.0/103.0/10
Visual integrity4.0/103.5/10

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

Qwen3.6-27B

A recognizable sunset beach with balanced palms, clean shapes and effective warm–cool contrast. Small animals and play equipment address the brief, but rudimentary anatomy, uncertain water contacts, sparse reflections and flat materials keep the drawing basic or uneven.

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

CategoryQwen3.6-27BStep 5 Preview
Task & likeness7.5/104.0/10
Anatomy & construction5.0/103.0/10
Space & placement5.5/103.5/10
Light & reflections5.5/103.5/10
Purposeful detail4.5/103.0/10
Artistry & character5.5/103.0/10
Materials & effects5.5/103.5/10
Visual integrity7.0/104.0/10

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

Qwen3.6-27B

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

Qwen3.6-27B

A readable cartoon with balanced colors, clean shapes and a clearly supported raccoon. Continuous body construction and modest shading deserve credit. Rudimentary limbs, unresolved steering connections, stiff gestures and schematic water effects limit physical credibility and finish.

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

CategoryQwen3.6-27BStep 5 Preview
Task & likeness4.5/104.0/10
Anatomy & construction3.5/104.5/10
Space & placement6.0/103.0/10
Light & reflections5.5/103.5/10
Purposeful detail5.5/104.0/10
Artistry & character4.0/103.5/10
Materials & effects5.5/103.0/10
Visual integrity2.5/103.0/10

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

Qwen3.6-27B

A lively, coherent illustration with recognizable pelican features, purposeful accessories and useful surface variation. Ambiguous neck layering, uncertain pedal engagement and an unresolved drivetrain limit construction. Aligned wheels and layered scenery establish placement, while inconsistent shadow direction and crowded overlaps constrain finish.

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

CategoryQwen3.6-27BStep 5 Preview
Task & likeness7.5/103.0/10
Anatomy & construction4.0/103.0/10
Space & placement6.5/103.0/10
Light & reflections5.0/103.0/10
Purposeful detail6.5/104.0/10
Artistry & character5.5/103.0/10
Materials & effects6.5/103.0/10
Visual integrity6.5/102.0/10

Benchmark task

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