STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Claude Fable 5.2 vs GPT-6 Astra

Claude Fable 5.2 leads GPT-6 Astra by 5.2 points on StealthMark, 79.8 to 74.6. It leads on 7 of 9 benchmarks, including both games, and GPT-6 Astra on 2. Claude Fable 5.2 scores higher on Ground Truth.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

79.8/100Overall rank 1/57
74.6/100Overall rank 2/57

General Intelligence

81.7/100
73.4/100

Visual Intelligence

76.0/100
76.9/100

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-6 Astra

Cost efficiency

How much Performance you get for your money.

  • Claude Fable 5.2Not measured

BENCHMARK BY BENCHMARK

Where each model leads

  • Claude Fable 5.2
  • GPT-6 Astra
  • Other models
  • Median

DATASHEET

Specs and pricing

  • Claude Fable 5.2
  • GPT-6 Astra
  • Other models
  • Median
PricePer 1M output tokens, input below
Claude Fable 5.2: No list priceGPT-6 Astra: $50$10 input
Context windowTokens per request, max output below
Claude Fable 5.2: Not publishedGPT-6 Astra: 1.05M128K max output
Output speedTokens per second, our measurement
Claude Fable 5.2: Not measuredGPT-6 Astra: 65tokens/s
Developer
Not publishedOpenAI
Released
Not published3 Sep 2026
Origin
Not publishedUnited States
Input → output
Not publishedText, image → text

Full datasheets, every price and sourceGPT-6 Astra ↗

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.

Claude Fable 5.2 77.2/100Rank 2/53

Survived 3 of 3
Foresight: complete playing field
Level 318 ptsTurn 20 / 20

GPT-6 Astra 76.1/100Rank 3/53

Survived 3 of 3
Foresight: complete playing field
Level 318 ptsTurn 20 / 20

Points per level

LevelClaude Fable 5.2GPT-6 Astra
Level 1Second Thoughts
27 ptsSurvived
27 ptsSurvived
Level 2Pressure Pot
12 ptsSurvived
11 ptsSurvived
Level 3Hide or Flight
18 ptsSurvived
18 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.

Claude Fable 5.2 100.0/100Rank 1/54

Cleared 5 of 5
Latch: complete playing field
Level 520.8 ptsTurn 26 / 40

GPT-6 Astra 87.6/100Rank 2/54

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

Points per level

LevelClaude Fable 5.2GPT-6 Astra
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
10.2 ptsClearedFinished early · 1 beacon left
10.2 ptsClearedFinished early · 1 beacon left
Level 3Relay vault
19.2 ptsCleared
19.2 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
18.2 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.8 ptsCleared
20.6 ptsCleared

Newton's Mirror

Same task instructions

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

The judgment

Claude Fable 5.2

The composition closely preserves the principal camera relationships. Visible cyan contact, elongated crimson coating and separate airborne black paint support the required interaction sequence, with a small crimson transport overshoot. Correct broad mirror placement coexists with major omissions in nested spherical imagery and simplified emitter mapping. Core score: 105.5/170; floor-damage reward: 0/10; combined total: 105.5/180.

GPT-6 Astra

Major placement and the visible contact sequence are convincing. Dense planar light repetition, recognizable spherical panel images and simplified nested sphere motifs provide useful optical structure. Missing outer chains, truncated distant sequences and incorrect bead-like belts still leave the recursive reflections substantially incomplete.

Score breakdown

CategoryClaude Fable 5.2GPT-6 Astra
State at 600 ms24.0/2525.0/25
Camera and placement15.0/1515.0/15
Reflections80.0/12070.0/120
Materials and scale8.5/1010.0/10
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

Claude Fable 5.2

The compact mantle, eight curling rays and quiet face closely realize the requested living emblem. Controlled arm contours, coherent overlaps and restrained ornament give the design character. Shallow depth, ribbon-like arm modeling and repeated highlight bands limit anatomical and lighting complexity without compromising the intact silhouette.

GPT-6 Astra

The sixfold silhouette, pale coloring, outward heads and central hexagon closely match the brief. Fine scales and soft shading support rounded volume. However, several crossings have conspicuous rectangular seams and weak contact shadows, making the weave feel assembled. Small heads have limited anatomical definition, and the repetitive texture conveys less organic life than requested.

Score breakdown

CategoryClaude Fable 5.2GPT-6 Astra
Task & likeness9.0/109.0/10
Anatomy & construction7.5/108.0/10
Space & placement7.0/107.5/10
Light & reflections7.0/107.0/10
Purposeful detail6.5/108.0/10
Artistry & character6.5/108.5/10
Materials & effects7.0/108.0/10
Visual integrity8.5/108.5/10

Benchmark task

Claude Fable 5.2

A coral squid with spreading arms tests connected anatomy, balanced composition and soft surface shading.

GPT-6 Astra

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.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

Claude Fable 5.2

A developed illustrative portrait with controlled facial shading, connected limbs, layered scenery and distinct aged-paint and gold effects. Its frontal torso, conspicuous smile and flattened fingers limit replication and anatomical precision. Decorative finish is stronger than the underlying seated construction.

GPT-6 Astra

Controlled hair contours, neckline detail, modeled sleeves and a layered river landscape give this recognizable portrait developed illustrative finish. The elongated face, largely frontal torso, crowded fingers and weakly established chair support limit replication, anatomical precision and spatial conviction. Small construction slips at the neck and jaw, a stray dark shape under the right cuff and an abruptly ending armrest bar weaken integrity.

Score breakdown

CategoryClaude Fable 5.2GPT-6 Astra
Task & likeness6.5/106.5/10
Anatomy & construction6.0/106.5/10
Space & placement6.0/106.5/10
Light & reflections6.5/106.5/10
Purposeful detail6.0/106.5/10
Artistry & character6.5/107.0/10
Materials & effects7.5/107.0/10
Visual integrity7.5/107.5/10

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

Claude Fable 5.2

A lively sunset beach with clear playful activity, purposeful small details and developed water reflections. Layering and supported placements hold the scene together. Schematic anatomy and the turtle's overhead viewpoint limit construction, space and artistry, while atmospheric and surface effects show greater refinement.

GPT-6 Astra

A richly composed sunset beach illustration with cohesive peach, mauve and teal colors. Sweeping palm fronds, a scalloped umbrella and curved shorelines frame the sun and its aligned reflection. Distinct animal silhouettes and carefully distributed beach details reward inspection. Simplified human and dog anatomy, slight dolphin splash cues and inconsistent equipment shadows limit physical conviction.

Score breakdown

CategoryClaude Fable 5.2GPT-6 Astra
Task & likeness9.0/109.0/10
Anatomy & construction8.0/107.5/10
Space & placement7.5/108.5/10
Light & reflections8.5/107.5/10
Purposeful detail8.5/108.5/10
Artistry & character8.0/108.5/10
Materials & effects7.5/107.5/10
Visual integrity8.0/107.5/10

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

Claude Fable 5.2

This benchmark has not been assessed yet.

GPT-6 Astra

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

Claude Fable 5.2

A controlled action illustration with expressive animals, demonstrated riding and steering, and an energetic layered wake. Purposeful small features and articulated poses strengthen the drawing. Simplified extremities, shallow character volume and limited physical lighting remain its principal constraints.

GPT-6 Astra

A controlled, expressive illustration with readable riding and steering, articulated poses and purposeful small details. Layered foam and coherent hull perspective establish motion and depth. Simplified paws, compressed control fittings and limited directional lighting constrain its physical sophistication.

Score breakdown

CategoryClaude Fable 5.2GPT-6 Astra
Task & likeness8.5/108.5/10
Anatomy & construction8.0/107.5/10
Space & placement7.5/107.5/10
Light & reflections7.0/106.5/10
Purposeful detail8.5/108.0/10
Artistry & character8.0/107.5/10
Materials & effects7.5/107.5/10
Visual integrity8.0/108.0/10

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

Same task instructions

Subject construction and spatial relationships.

The judgment

Claude Fable 5.2

A strong illustration with an expressive pelican, readable riding contacts and carefully constructed bicycle details. Layered plumage, basket weave and coastal scenery reward inspection. Continuous attachments support the action, while limited visible leg articulation, modest volume and weakly directional foreground lighting constrain physical sophistication.

GPT-6 Astra

The pelican's long bill, flowing scarf and warm coastal palette create a charming, balanced illustration. Wheels, spokes and frame are largely coherent, but neither wing reaches the handlebars, and the rear leg's pedal contact is unclear. Flat lighting and simplified surfaces limit depth despite clean outlines and attractive feather detail.

Score breakdown

CategoryClaude Fable 5.2GPT-6 Astra
Task & likeness9.0/108.0/10
Anatomy & construction8.0/107.0/10
Space & placement7.5/107.5/10
Light & reflections6.5/107.0/10
Purposeful detail8.0/108.0/10
Artistry & character7.5/108.0/10
Materials & effects7.0/107.5/10
Visual integrity8.0/108.0/10

Benchmark task

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