STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-5.6 Luna vs Qwen3.8-Max-0902

Qwen3.8-Max-0902 leads GPT-5.6 Luna by 24.6 points on StealthMark, 62.4 to 37.8. It leads on all 9 benchmarks. Qwen3.8-Max-0902 scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

37.8/100Overall rank 43/58
62.4/100Overall rank 9/58

General Intelligence

30.4/100
61.6/100

Visual Intelligence

50.2/100
63.9/100

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.

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-5.6 Luna
  • Qwen3.8-Max-0902
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-5.6 Luna is 4.1× cheaper per output token and runs 2.4× faster in our speed test. Qwen3.8-Max-0902 scores higher on StealthMark. Both take about 1.05M tokens of context.

  • GPT-5.6 Luna
  • Qwen3.8-Max-0902
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-5.6 Luna: $1.204.1× cheaper$0.20 inputQwen3.8-Max-0902: $4.95$1.65 input
Context windowTokens per request, max output below
GPT-5.6 Luna: 1.05MTied128K max outputQwen3.8-Max-0902: 1MTied128K max output
Output speedTokens per second, our measurement
GPT-5.6 Luna: 1812.4× fastertokens/sQwen3.8-Max-0902: 76tokens/s
SizeTotal and active parameters
GPT-5.6 Luna: Not disclosedQwen3.8-Max-0902: 2.4T95B activeEstimated
Developer
OpenAIQwen / Alibaba Cloud
Released
9 Jul 20262 Sep 2026
Origin
United StatesChina
Input → output
Text, image → textBoth
Architecture
Not publishedMixture-of-Experts; hosted version based on the open Qwen3.8-2.4T-A95B

Full datasheets, every price and sourceGPT-5.6 Luna ↗Qwen3.8-Max-0902 ↗

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-Max-0902 72.4/100Rank 5/54

Survived 2 of 3
Foresight: complete playing field
Level 316 ptsTurn 20 / 20

Points per level

LevelGPT-5.6 LunaQwen3.8-Max-0902
Level 1Second Thoughts
4 ptsOut of lives
27 ptsSurvived
Level 2Pressure Pot
6 ptsOut of lives
12 ptsOut of lives
Level 3Hide or Flight
8 ptsOut of lives
16 ptsSurvived

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-Max-0902 82.6/100Rank 7/55

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

Points per level

LevelGPT-5.6 LunaQwen3.8-Max-0902
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
19.2 ptsCleared
Level 4Passing bay
17 ptsClearedFinished early · 3 beacons left
18.2 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
20.6 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-Max-0902

The central sphere and differentiated cyan/crimson interaction are supported. The tiny highlighted object above the sphere provides partial airborne-black evidence. The few isolated sphere and panel images preserve limited optical relationships, but most of the repeating mirror-room structure is missing. Core score: 64.5/170; including the floor-damage reward: 64.5/180.

Score breakdown

CategoryGPT-5.6 LunaQwen3.8-Max-0902
State at 600 ms15.0/2523.0/25
Camera and placement4.0/1512.0/15
Reflections3.5/12029.0/120
Materials and scale6.5/108.0/10
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-Max-0902

A coherent ornamental illustration with balanced framing, appealing color and legible magical accessories. The disconnected raised wrist, incorrect raised-arm side and palm orientation, bear-like facial proportions and shallow material modeling limit execution. Clean decoration and compact spatial balance remain strengths.

Score breakdown

CategoryGPT-5.6 LunaQwen3.8-Max-0902
Task & likeness7.5/107.5/10
Anatomy & construction6.0/106.5/10
Space & placement6.5/108.0/10
Light & reflections5.0/107.0/10
Purposeful detail5.5/107.5/10
Artistry & character6.0/107.0/10
Materials & effects5.0/107.5/10
Visual integrity6.0/105.5/10

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-Max-0902

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-Max-0902

A recognizable, cohesive Mona Lisa interpretation with readable landscape layers and a restrained expression. Continuous body construction and clean contours support readability, but broad hands, simplified drapery, frontal symmetry and limited facial volume keep the execution basic and uneven.

Score breakdown

CategoryGPT-5.6 LunaQwen3.8-Max-0902
Task & likeness3.5/104.5/10
Anatomy & construction3.5/103.5/10
Space & placement4.0/105.0/10
Light & reflections4.5/105.0/10
Purposeful detail4.0/105.0/10
Artistry & character4.0/105.0/10
Materials & effects3.5/103.5/10
Visual integrity4.5/105.0/10

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-Max-0902

A strong stylized beach illustration with coherent sunset color, lively dolphin arcs and balanced activity. Clean contours, readable ground contact and an aligned reflection support the finish. Schematic anatomy, sparse small-subject features, flat materials and repetitive water highlights limit physical depth and refinement.

Score breakdown

CategoryGPT-5.6 LunaQwen3.8-Max-0902
Task & likeness7.5/108.5/10
Anatomy & construction4.0/107.5/10
Space & placement5.5/107.5/10
Light & reflections4.0/108.0/10
Purposeful detail6.5/107.0/10
Artistry & character3.5/107.5/10
Materials & effects4.0/106.5/10
Visual integrity3.5/108.5/10

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-Max-0902

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-Max-0902

The riding arrangement and steering action are readable, supported by coherent visible attachments and useful character details. Clean shapes, strong color separation and clustered foam make the scene appealing and active. Stiff anatomy, crowded controls, limited directional lighting and simple surface treatments constrain sophistication.

Score breakdown

CategoryGPT-5.6 LunaQwen3.8-Max-0902
Task & likeness7.0/108.0/10
Anatomy & construction5.0/107.0/10
Space & placement6.5/107.0/10
Light & reflections6.0/106.5/10
Purposeful detail6.5/107.0/10
Artistry & character4.5/106.5/10
Materials & effects5.5/106.0/10
Visual integrity5.0/107.5/10

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-Max-0902

An appealing graphic illustration with a recognizable pelican, readable bicycle and clean coastal composition. Steering contact and one connected pedal support the action. Ambiguous neck-to-torso construction, an unclear opposing pedal connection, shallow space and limited material and lighting effects constrain its execution.

Score breakdown

CategoryGPT-5.6 LunaQwen3.8-Max-0902
Task & likeness8.5/108.5/10
Anatomy & construction5.5/106.5/10
Space & placement7.5/107.0/10
Light & reflections6.5/106.0/10
Purposeful detail6.5/107.5/10
Artistry & character5.5/107.5/10
Materials & effects7.0/106.0/10
Visual integrity6.5/108.0/10

Benchmark task

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