STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-5.6 Luna vs Qwen3.8-Flash

Qwen3.8-Flash leads GPT-5.6 Luna by 8.4 points on StealthMark, 46.2 to 37.8. It leads on all 9 benchmarks. Qwen3.8-Flash scores higher on Beach, with its largest category advantage in artistry & character.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

37.8/100Overall rank 43/58
46.2/100Overall rank 29/58

General Intelligence

30.4/100
38.3/100

Visual Intelligence

50.2/100
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 Luna

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

DATASHEET

Specs and pricing

GPT-5.6 Luna runs 2.4× faster in our speed test. Qwen3.8-Flash scores higher on StealthMark and is 3.1× cheaper per output token. Both take about 1.05M tokens of context.

  • GPT-5.6 Luna
  • Qwen3.8-Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-5.6 Luna: $1.20$0.20 inputQwen3.8-Flash: $0.383.1× cheaper$0.11 input
Context windowTokens per request, max output below
GPT-5.6 Luna: 1.05MTied128K max outputQwen3.8-Flash: 1MTied128K max output
Output speedTokens per second, our measurement
GPT-5.6 Luna: 1812.4× fastertokens/sQwen3.8-Flash: 75tokens/s
SizeTotal and active parameters
GPT-5.6 Luna: 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 Luna ↗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 Luna 25.1/100Rank 41/54

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 15 / 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 LunaQwen3.8-Flash
Level 1Second Thoughts
4 ptsOut of lives
26 ptsSurvived
Level 2Pressure Pot
6 ptsOut of lives
3 ptsOut of lives
Level 3Hide or Flight
8 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 Luna 52.9/100Rank 28/55

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 LunaQwen3.8-Flash
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
8.6 ptsClearedFinished early · 1 beacon left
9.8 ptsCleared
Level 3Relay vault
18 ptsCleared
18.8 ptsCleared
Level 4Passing bay
17 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 Luna

The room enclosure has coherent symmetric perspective, with the overhead panel, sphere and black aligned centrally. The sphere and airborne black occupy substantially lower positions than the reference framing, inconsistent with the prescribed camera aim. The diagonal crimson streak does not establish the required surface transport. Faint wall sphere images provide limited mirrored correspondence, but the shallow floor image, missing receding chains, absent nested sphere imagery and sparse emitter mapping leave most reflection structure unsupported.

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 LunaQwen3.8-Flash
State at 600 ms15.0/2519.0/25
Camera and placement4.0/153.5/15
Reflections3.5/1209.5/120
Materials and scale6.5/104.0/10
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 Luna

Six pale, outward-facing heads and six rounded lobes make the knot recognizable. The central hexagonal opening remains clear. However, broad gray crossing panels flatten the weave, several inner joins resemble capped strips, and sparse oversized scale marks leave the bodies looking more like decorated ribbons than living snakes.

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 LunaQwen3.8-Flash
Task & likeness7.5/108.0/10
Anatomy & construction6.0/106.0/10
Space & placement6.5/107.0/10
Light & reflections5.0/107.5/10
Purposeful detail5.5/107.5/10
Artistry & character6.0/106.0/10
Materials & effects5.0/107.5/10
Visual integrity6.0/108.0/10

Benchmark task

GPT-5.6 Luna

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 Luna

The central portrait, dark clothing, crossed hands and muted landscape clearly evoke Mona Lisa. Replication is limited by the elongated face, conspicuous eyes and simplified smile. Overlapping fingers have uncertain anatomy, while broad gradients and heavy outlines flatten the portrait. The composition and restrained palette remain coherent.

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 LunaQwen3.8-Flash
Task & likeness3.5/105.0/10
Anatomy & construction3.5/104.5/10
Space & placement4.0/105.5/10
Light & reflections4.5/105.5/10
Purposeful detail4.0/105.5/10
Artistry & character4.0/105.5/10
Materials & effects3.5/105.5/10
Visual integrity4.5/105.5/10

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 Luna

The warm sunset, palm silhouette and varied beach activities create an appealing, readable composition. Animals, birds and a broad sun reflection satisfy the brief. Drawing remains elementary: angular airborne sea animals lack splash or convincing motion, the crab's claws are awkwardly constructed, and repeated reflection bands suggest a stepped platform. Clean outlines and pleasant colors exceed the anatomical and spatial sophistication.

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 LunaQwen3.8-Flash
Task & likeness7.5/109.0/10
Anatomy & construction4.0/107.0/10
Space & placement5.5/108.0/10
Light & reflections4.0/107.5/10
Purposeful detail6.5/108.5/10
Artistry & character3.5/108.0/10
Materials & effects4.0/106.5/10
Visual integrity3.5/107.0/10

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

GPT-5.6 Luna

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 Luna

Expressive animals, a striped tail and clean outlines make the scene appealing and readable. The raccoon sits convincingly on the dog's back, but the overlapping steering paws are ambiguous and the control stem stops above the hull. Broad wake shapes suggest motion; the glowing sun lacks a corresponding water reflection.

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 LunaQwen3.8-Flash
Task & likeness7.0/107.0/10
Anatomy & construction5.0/105.5/10
Space & placement6.5/106.5/10
Light & reflections6.0/105.5/10
Purposeful detail6.5/107.0/10
Artistry & character4.5/106.5/10
Materials & effects5.5/105.5/10
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 Luna

A recognizable pelican cyclist with an expressive profile, balanced composition and controlled outlines. Head, neck and torso connect coherently. The bicycle wheels and frame are convincing, but overlapping feet obscure pedal contact, the drivetrain lacks a clear chain, and the wing's handlebar grip is schematic. Atmospheric color succeeds more strongly than directional lighting or material depth.

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 LunaQwen3.8-Flash
Task & likeness8.5/108.5/10
Anatomy & construction5.5/108.0/10
Space & placement7.5/107.5/10
Light & reflections6.5/106.5/10
Purposeful detail6.5/108.0/10
Artistry & character5.5/108.0/10
Materials & effects7.0/107.0/10
Visual integrity6.5/107.5/10

Benchmark task

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