STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-5.6 Terra vs Qwen3.8-Flash

Qwen3.8-Flash leads GPT-5.6 Terra by 0.4 points on StealthMark, 46.2 to 45.8. It leads on 6 of 9 benchmarks and GPT-5.6 Terra on 3, including both games. Qwen3.8-Flash scores higher on Beach, with its largest category advantage in artistry & character.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

45.8/100Overall rank 30/58
46.2/100Overall rank 29/58

General Intelligence

41.9/100
38.3/100

Visual Intelligence

52.7/100
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

  • GPT-5.6 Terra

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 Terra
  • Qwen3.8-Flash
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-5.6 Terra runs 35% faster in our speed test. Qwen3.8-Flash scores higher on StealthMark and is 31× cheaper per output token. Both take about 1.05M tokens of context.

  • GPT-5.6 Terra
  • Qwen3.8-Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-5.6 Terra: $12$2 inputQwen3.8-Flash: $0.3831× cheaper$0.11 input
Context windowTokens per request, max output below
GPT-5.6 Terra: 1.05MTied128K max outputQwen3.8-Flash: 1MTied128K max output
Output speedTokens per second, our measurement
GPT-5.6 Terra: 10235% fastertokens/sQwen3.8-Flash: 75tokens/s
SizeTotal and active parameters
GPT-5.6 Terra: 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 Terra ↗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 Terra 30.1/100Rank 36/54

Survived 0 of 3
Foresight: complete playing field
Level 36 ptsTurn 7 / 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 TerraQwen3.8-Flash
Level 1Second Thoughts
5 ptsOut of lives
26 ptsSurvived
Level 2Pressure Pot
9 ptsOut of lives
3 ptsOut of lives
Level 3Hide or Flight
6 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 Terra 80.0/100Rank 11/55

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 TerraQwen3.8-Flash
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
9.8 ptsCleared
Level 3Relay vault
19.2 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 Terra

The real sphere and airborne black blob are substantially too low in the complete frame after accounting for aspect ratio. The first wall and floor reflections have incompatible placement, relative size or silhouette. Both lateral regions lack the references' receding lane-and-chain organization. The few recognizable mirror images provide limited optical structure. The main, side and floor spheres replace nested mirror imagery with smooth bands, while sparse planar light patches and broad spherical highlights fail to establish coherent repeated emitter mapping.

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 TerraQwen3.8-Flash
State at 600 ms24.0/2519.0/25
Camera and placement6.0/153.5/15
Reflections7.0/1209.5/120
Materials and scale5.5/104.0/10
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 Terra

Six ivory heads and rounded lobes create a striking radial emblem around a clear hexagonal opening. Soft shading gives the bodies volume, but abrupt rectangular and diagonal band endings make the continuous alternating weave ambiguous. Repetitive scale lines and simplified faces convey an ornamental serpent more convincingly than living anatomy.

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 TerraQwen3.8-Flash
Task & likeness7.5/108.0/10
Anatomy & construction5.5/106.0/10
Space & placement7.0/107.0/10
Light & reflections7.5/107.5/10
Purposeful detail6.5/107.5/10
Artistry & character5.5/106.0/10
Materials & effects6.5/107.5/10
Visual integrity5.0/108.0/10

Benchmark task

GPT-5.6 Terra

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 Terra

The dark clothing, central portrait and restrained smile evoke the Mona Lisa, but replication is limited by the broad face, elongated neck, nearly frontal pose and indistinct landscape. Soft gradients give the face some volume. Crossed arms become rounded masses without readable fingers or wrists, and the expression lacks the original's subtlety. Clean framing and curves support an otherwise basic, uneven portrait.

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 TerraQwen3.8-Flash
Task & likeness4.0/105.0/10
Anatomy & construction3.0/104.5/10
Space & placement4.5/105.5/10
Light & reflections5.0/105.5/10
Purposeful detail4.0/105.5/10
Artistry & character4.0/105.5/10
Materials & effects4.0/105.5/10
Visual integrity6.0/105.5/10

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 Terra

Warm sunset gradients, framing palms and colorful beach activities create an appealing scene. Animals, birds and a sun reflection fulfill the brief. The dog and turtle remain schematic, foreground depth is shallow, and the reflection forms rigid bands. Clean silhouettes and readable accessories support a competent illustration, but limited anatomy, material variation and lighting keep it below exceptional.

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 TerraQwen3.8-Flash
Task & likeness7.5/109.0/10
Anatomy & construction5.0/107.0/10
Space & placement6.0/108.0/10
Light & reflections5.0/107.5/10
Purposeful detail6.5/108.5/10
Artistry & character5.0/108.0/10
Materials & effects5.5/106.5/10
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 Terra

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 Terra

Expressive faces, a recognizable raccoon perched on the dog, and a sweeping wake make an appealing cartoon. The principal weakness is the steering interaction: the dog's paw sits beside the control assembly without a convincing handlebar grip. Bold outlines and coherent layering provide polish, while simplified shading, compressed seating geometry and angular splashes limit depth and physical credibility.

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 TerraQwen3.8-Flash
Task & likeness7.5/107.0/10
Anatomy & construction5.0/105.5/10
Space & placement7.0/106.5/10
Light & reflections6.0/105.5/10
Purposeful detail7.0/107.0/10
Artistry & character5.0/106.5/10
Materials & effects7.0/105.5/10
Visual integrity7.5/107.0/10

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 Terra

The oversized bill, expressive eye and balanced twilight palette make the cyclist immediately readable. Clean contours and wheel details support the illustration, but the rabbit-like head tufts weaken pelican likeness. The wing does not clearly grip the handlebar, pedal contact is uneven, and the drivetrain is incomplete. Lighting remains mostly decorative.

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 TerraQwen3.8-Flash
Task & likeness6.0/108.5/10
Anatomy & construction6.0/108.0/10
Space & placement7.0/107.5/10
Light & reflections6.5/106.5/10
Purposeful detail7.0/108.0/10
Artistry & character6.5/108.0/10
Materials & effects6.5/107.0/10
Visual integrity7.0/107.5/10

Benchmark task

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