STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-5.6 Sol vs Qwen3.8-Flash

GPT-5.6 Sol leads Qwen3.8-Flash by 7.5 points on StealthMark, 53.7 to 46.2. Qwen3.8-Flash leads on 5 of 9 benchmarks and GPT-5.6 Sol on 4, including both games. GPT-5.6 Sol 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

53.7/100Overall rank 15/58
46.2/100Overall rank 29/58

General Intelligence

51.7/100
38.3/100

Visual Intelligence

57.4/100
59.5/100

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.

Open or local

Local modelOpen model · Qwen Community 1.0

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-5.6 Sol
  • Qwen3.8-Flash
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-5.6 Sol scores higher on StealthMark. Qwen3.8-Flash is 52× cheaper per output token. Both take about 1.05M tokens of context.

  • GPT-5.6 Sol
  • Qwen3.8-Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-5.6 Sol: $20$4 inputQwen3.8-Flash: $0.3852× cheaper$0.11 input
Context windowTokens per request, max output below
GPT-5.6 Sol: 1.05MTied128K max outputQwen3.8-Flash: 1MTied128K max output
Output speedTokens per second, our measurement
GPT-5.6 Sol: 81Tiedtokens/sQwen3.8-Flash: 75Tiedtokens/s
SizeTotal and active parameters
GPT-5.6 Sol: Not disclosedQwen3.8-Flash: 180B6B activeEstimated
Developer
OpenAIQwen / Alibaba Cloud
Released
9 Jul 202626 Aug 2026
Origin
United StatesChina
Input → output
Text, image → textText, image, video → text
Architecture
Not publishedHosted Flash based on Flash-Next: sparse attention and n-gram memory; Flash-Next previews Qwen 4 architecture

Full datasheets, every price and sourceGPT-5.6 Sol ↗Qwen3.8-Flash ↗

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.

GPT-5.6 Sol 62.9/100Rank 9/54

Survived 1 of 3
Foresight: complete playing field
Level 311 ptsTurn 17 / 20

Qwen3.8-Flash 29.7/100Rank 38/54

Survived 1 of 3
Foresight: complete playing field
Level 35 ptsTurn 10 / 20

Points per level

LevelGPT-5.6 SolQwen3.8-Flash
Level 1Second Thoughts
27 ptsSurvived
26 ptsSurvived
Level 2Pressure Pot
10 ptsOut of lives
3 ptsOut of lives
Level 3Hide or Flight
11 ptsOut of lives
5 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.

GPT-5.6 Sol 83.6/100Rank 6/55

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

Qwen3.8-Flash 69.8/100Rank 20/55

Cleared 5 of 5
Latch: complete playing field
Level 520 ptsTurn 30 / 40

Points per level

LevelGPT-5.6 SolQwen3.8-Flash
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
10.2 ptsClearedFinished early · 1 beacon left
9.8 ptsCleared
Level 3Relay vault
18.8 ptsCleared
18.8 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
17.2 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
20 ptsCleared

Newton's Mirror

Same task instructions

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

The judgment

GPT-5.6 Sol

The central sphere and paint ordering are supported, but a frontal, centrally converging chamber replaces the required corner perspective. The first wall and floor images have incorrect placement and scale relationships. Sparse reflection cues remain, while continuous outer chains, open lateral sightlines, dense planar light sequences and curved nested spherical imagery are largely missing.

Qwen3.8-Flash

The full-frame illustration supports a central steel sphere, an airborne black blob and the relative ordering of cyan and crimson. Its faint floor return and symmetric repetitions provide sparse mirror structure; outer chains, large reflected images, nested imagery and emitter mapping remain deficient. Vertical framing is substantially displaced, and paint contact histories remain unresolved.

Score breakdown

CategoryGPT-5.6 SolQwen3.8-Flash
State at 600 ms23.0/2519.0/25
Camera and placement6.0/153.5/15
Reflections11.0/1209.5/120
Materials and scale7.5/104.0/10
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

GPT-5.6 Sol

Six evenly spaced lobes, outward-facing heads and a clear central hexagon establish the requested knot. The ivory silhouette is controlled, but broad crossing bands resemble rigid strips, shading provides limited muscular volume, and repetitive scale lines extend across black loop openings. Small oval heads have readable eyes and mouths but limited anatomical character or moist surface detail.

Qwen3.8-Flash

A coherent, appealing fantasy illustration with disciplined framing, luminous teal accents and consistent ornament. Most requested elements are clearly present. The bear-like facial proportions, lowered resting hand, obscured bent-leg construction and limited fabric modeling constrain likeness and anatomical clarity; glow effects are attractive but weakly integrated with surrounding surfaces.

Score breakdown

CategoryGPT-5.6 SolQwen3.8-Flash
Task & likeness7.5/108.0/10
Anatomy & construction6.0/106.0/10
Space & placement7.0/107.0/10
Light & reflections5.0/107.5/10
Purposeful detail6.0/107.5/10
Artistry & character6.5/106.0/10
Materials & effects4.5/107.5/10
Visual integrity6.0/108.0/10

Benchmark task

GPT-5.6 Sol

A pale serpent woven into an interlocking knot tests connected anatomy, repeated structure and readable overlaps. Organic surface detail must work with the overall geometry.

Qwen3.8-Flash

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

GPT-5.6 Sol

The crossed hands, dark dress and winding landscape establish the Mona Lisa composition. Replication is limited by enlarged eyes, an elongated face and a more frontal pose. Broad gradients suggest volume, but outlined features and flattened, overlapping fingers weaken the portrait. The frame and restrained palette unify the image; visible grain adds texture without convincing painterly transitions.

Qwen3.8-Flash

The dark dress, crossed hands and hazy landscape evoke the Mona Lisa, but replication is limited by a generic frontal face, coarse smile and poorly articulated fingers. The gold frame has clearer definition than the portrait. Heavy mottling obscures features, while soft shading provides some volume without convincing anatomical detail.

Score breakdown

CategoryGPT-5.6 SolQwen3.8-Flash
Task & likeness4.5/105.0/10
Anatomy & construction4.0/104.5/10
Space & placement5.5/105.5/10
Light & reflections5.0/105.5/10
Purposeful detail5.0/105.5/10
Artistry & character4.5/105.5/10
Materials & effects5.5/105.5/10
Visual integrity6.5/105.5/10

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

GPT-5.6 Sol

Clear subject coverage, developed beach details and coordinated atmospheric effects support a coherent illustration. The large dolphin floats in the sky above the horizon with no water contact or splash, and the kite line ends at the flyer's upper arm without a clear grip. Schematic tube-limbed anatomy and the turtle's overhead viewpoint against the low horizon are further limits.

Qwen3.8-Flash

Sweeping palms, coordinated sunset colors and a central reflection create an expressive beach composition with clear depth. Birds, animals and varied activities thoroughly realize the brief. Small figures and animal anatomy remain rudimentary, water movement is schematic, and contact shadows are weak. Scattered foreground details and the clipped orange disk limit the finish.

Score breakdown

CategoryGPT-5.6 SolQwen3.8-Flash
Task & likeness8.5/109.0/10
Anatomy & construction5.0/107.0/10
Space & placement5.5/108.0/10
Light & reflections7.0/107.5/10
Purposeful detail7.0/108.5/10
Artistry & character6.0/108.0/10
Materials & effects7.0/106.5/10
Visual integrity5.0/107.0/10

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.

The judgment

GPT-5.6 Sol

This benchmark has not been assessed yet.

Qwen3.8-Flash

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

GPT-5.6 Sol

Expressive faces, bold silhouettes and layered waves make an appealing cartoon. The raccoon sits convincingly behind the dog's shoulders, and the dog's forward paw reaches the steering grip. Steering construction and seated support remain somewhat ambiguous. The glowing sunset lacks a corresponding warm reflection or consistent illumination on the riders.

Qwen3.8-Flash

The raccoon clearly rides the dog's back, with expressive features and appealing blue-orange color contrast. The dog's paws do not clearly operate connected controls, and the shallow vehicle lacks convincing jet ski construction. Clean outlines support the cartoon style, but generic shading and blurred water streaks limit depth and motion.

Score breakdown

CategoryGPT-5.6 SolQwen3.8-Flash
Task & likeness6.5/107.0/10
Anatomy & construction5.0/105.5/10
Space & placement6.5/106.5/10
Light & reflections6.5/105.5/10
Purposeful detail7.5/107.0/10
Artistry & character5.0/106.5/10
Materials & effects7.0/105.5/10
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

Same task instructions

Subject construction and spatial relationships.

The judgment

GPT-5.6 Sol

The expressive pelican and balanced coastal composition remain appealing, but a sky-colored slit between the neck contours above the wing leaves the central anatomy incoherent. This visible construction and layering defect prevents a clean-integrity assessment. Clustered feet lack clear pedal contacts and the chain routing is schematic; lighting and water reflections remain graphic.

Qwen3.8-Flash

The pelican's expressive face, oversized bill and flowing scarf create an appealing focal point. The bicycle has recognizable frame, chain and wheel construction, but the far foot lacks a clear pedal connection and the wing's steering contact is ambiguous. Clean contours and gentle gradients support the illustration; simplified volume and weak directional shadows limit depth.

Score breakdown

CategoryGPT-5.6 SolQwen3.8-Flash
Task & likeness8.5/108.5/10
Anatomy & construction5.0/108.0/10
Space & placement7.5/107.5/10
Light & reflections7.5/106.5/10
Purposeful detail8.0/108.0/10
Artistry & character6.5/108.0/10
Materials & effects7.0/107.0/10
Visual integrity4.5/107.5/10

Benchmark task

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