STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-5.6 Luna vs Callstack Apex

Callstack Apex leads GPT-5.6 Luna by 11.7 points on StealthMark, 49.5 to 37.8. It leads on 7 of the 8 benchmarks with results for both and GPT-5.6 Luna on 1, including Latch. Pixel Canary scores higher on Newton's Mirror, with its largest category advantage in camera and placement.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

37.8/100Overall rank 43/58
49.5/100Overall rank 22/58

General Intelligence

30.4/100
40.4/100

Visual Intelligence

50.2/100
59.6/100

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
  • Callstack Apex
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-5.6 Luna is 2.5× cheaper per output token and takes 4× more context. Callstack Apex scores higher on StealthMark and runs 41% faster in our speed test.

  • GPT-5.6 Luna
  • Callstack Apex
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-5.6 Luna: $1.202.5× cheaper$0.20 inputCallstack Apex: $3$0.50 input
Context windowTokens per request, max output below
GPT-5.6 Luna: 1.05M4× larger128K max outputCallstack Apex: 256K
Output speedTokens per second, our measurement
GPT-5.6 Luna: 181tokens/sCallstack Apex: 25541% fastertokens/s
Developer
OpenAICallstack
Released
9 Jul 20261 Oct 2026
Origin
United StatesPoland
Input → output
Text, image → textText → text
Architecture
Not publishedQwen foundation with Callstack domain post-training for React and React Native

Full datasheets, every price and sourceGPT-5.6 Luna ↗Callstack Apex ↗

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

Points per level

LevelGPT-5.6 LunaCallstack Apex
Level 1Second Thoughts
4 ptsOut of lives
No run
Level 2Pressure Pot
6 ptsOut of lives
No run
Level 3Hide or Flight
8 ptsOut of lives
No run

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

Callstack Apex 100.0/100Rank 47/551 of 5 levels

1 of 5 played
Latch: complete playing field
Level 15.2 ptsTurn 6 / 12

Points per level

LevelGPT-5.6 LunaCallstack Apex
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
8.6 ptsClearedFinished early · 1 beacon left
Pending
Level 3Relay vault
18 ptsCleared
Pending
Level 4Passing bay
17 ptsClearedFinished early · 3 beacons left
Not played
Level 5Second thoughts
20.6 ptsCleared
Not played

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.

Callstack Apex

The principal sphere placement and paint contact sequence are supported. Isolated sphere and panel images provide limited optical structure, but missing lateral chains and side-floor continuations prevent a coherent repeating mirror room. The main and reflected spheres lack ordered curved nested imagery, while sparse planar emitter images and incomplete spherical emitter mapping leave most of the reflection system unsupported.

Score breakdown

CategoryGPT-5.6 LunaCallstack Apex
State at 600 ms15.0/2520.0/25
Camera and placement4.0/1513.0/15
Reflections3.5/12010.0/120
Materials and scale6.5/107.0/10
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

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.

Callstack Apex

The cheerful yellow bird, cream eyes, orange features and miniature teal console closely match the brief. Clean block edges, restrained colors and soft shadows create an appealing composition. The body reads more like a gridded disc than a fully cubic sphere, and the outlined left wing has limited volume. The right wing reaches the cyan block, though its grip is ambiguous.

Score breakdown

CategoryGPT-5.6 LunaCallstack Apex
Task & likeness7.5/108.5/10
Anatomy & construction6.0/107.0/10
Space & placement6.5/107.5/10
Light & reflections5.0/107.5/10
Purposeful detail5.5/107.5/10
Artistry & character6.0/107.0/10
Materials & effects5.0/107.0/10
Visual integrity6.0/107.5/10

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.

Callstack Apex

A rounded bird built from small cubes explores a miniature machine. The scene tests block construction, expressive proportions, contact and soft lighting.

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.

Callstack Apex

The framed portrait recalls Mona Lisa through dark hair, folded arms and a hazy landscape. Replication is limited by wide, staring eyes, an elongated neck and a downturned mouth. The overlapping hands lack convincing finger and wrist construction. Soft tonal shading suggests volume, but pervasive blur obscures clothing, landscape and anatomical detail.

Score breakdown

CategoryGPT-5.6 LunaCallstack Apex
Task & likeness3.5/103.5/10
Anatomy & construction3.5/104.0/10
Space & placement4.0/104.5/10
Light & reflections4.5/106.0/10
Purposeful detail4.0/104.5/10
Artistry & character4.0/104.5/10
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

Different 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.

Callstack Apex

A cohesive sunset beach illustration with lively wildlife, playful accents, and an appealing warm-to-purple palette. Palm framing and the aligned sun reflection organize the scene, while connected silhouettes keep the activities readable. Schematic joints, ambiguous dolphin junctions, loosely matched reflections, and repetitive surface marks limit construction, lighting coherence, and material depth.

Score breakdown

CategoryGPT-5.6 LunaCallstack Apex
Task & likeness7.5/108.5/10
Anatomy & construction4.0/104.5/10
Space & placement5.5/107.5/10
Light & reflections4.0/105.5/10
Purposeful detail6.5/107.5/10
Artistry & character3.5/106.5/10
Materials & effects4.0/107.0/10
Visual integrity3.5/104.0/10

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

GPT-5.6 Luna

This benchmark has not been assessed yet.

Callstack Apex

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

Multiple instruction versions

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.

Callstack Apex

The raccoon clearly rides the dog's back, and the dog's paws reach the jet ski controls. Expressive faces, a sweeping tail and a strong sunset composition give the illustration character. Limbs remain connected, but the dog's foreleg joints and vehicle seating are loosely constructed. Angular splashes convey speed more successfully than convincing water displacement; lighting and reflections remain decorative.

Score breakdown

CategoryGPT-5.6 LunaCallstack Apex
Task & likeness7.0/109.0/10
Anatomy & construction5.0/107.0/10
Space & placement6.5/107.5/10
Light & reflections6.0/107.0/10
Purposeful detail6.5/108.5/10
Artistry & character4.5/107.5/10
Materials & effects5.5/107.0/10
Visual integrity5.0/108.0/10

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

Different 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.

Callstack Apex

An appealing cartoon with a distinctive pelican, expressive eye, warm bill and carefully drawn bicycle wheels. The wing reaches the handlebar, but the feet do not clearly engage the pedals, weakening the riding mechanics. Layered hills create depth; limited ground shadows weaken contact. Clean curves and purposeful feather details give the illustration polish.

Score breakdown

CategoryGPT-5.6 LunaCallstack Apex
Task & likeness8.5/108.5/10
Anatomy & construction5.5/106.5/10
Space & placement7.5/107.5/10
Light & reflections6.5/107.5/10
Purposeful detail6.5/108.5/10
Artistry & character5.5/108.0/10
Materials & effects7.0/107.5/10
Visual integrity6.5/108.0/10

Benchmark task

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