STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Claude Opus 5.5 vs GPT-6.1 Terra Low

Claude Opus 5.5 leads GPT-6.1 Terra Low by 31.3 points on StealthMark, 72.6 to 41.3. It leads on all 9 benchmarks. Claude Opus 5.5 scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

72.6/100Overall rank 2/55
41.3/100Overall rank 35/55

General Intelligence

71.3/100
34.3/100

Visual Intelligence

75.0/100
53.1/100

BENCHMARK BY BENCHMARK

Where each model leads

  • Claude Opus 5.5
  • GPT-6.1 Terra Low
  • Other models
  • Median

DATASHEET

Specs and pricing

  • Claude Opus 5.5
  • GPT-6.1 Terra Low
  • Other models
  • Median
PricePer 1M output tokens, input below
Claude Opus 5.5: $20$4 inputGPT-6.1 Terra Low: No list price
Context windowTokens per request, max output below
Claude Opus 5.5: 1M128K max outputGPT-6.1 Terra Low: Not published
Output speedTokens per second, our measurement
Claude Opus 5.5: 166tokens/sGPT-6.1 Terra Low: Not measured
Developer
AnthropicNot published
Released
22 Sep 2026Not published
Origin
United StatesNot published
Input → output
Text, image → textNot published

Full datasheets, every price and sourceClaude Opus 5.5 ↗

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 Opus 5.5 66.3/100Rank 5/51

Survived 3 of 3
Foresight: complete playing field
Level 39 ptsTurn 20 / 20

GPT-6.1 Terra Low 36.1/100Rank 26/51

Survived 1 of 3
Foresight: complete playing field
Level 39 ptsTurn 20 / 20

Points per level

LevelClaude Opus 5.5GPT-6.1 Terra Low
Level 1Second Thoughts
27 ptsSurvived
4 ptsOut of lives
Level 2Pressure Pot
11 ptsSurvived
8 ptsOut of lives
Level 3Hide or Flight
9 ptsSurvived
9 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 Opus 5.5 87.6/100Rank 1/52

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

GPT-6.1 Terra Low 62.4/100Rank 23/52

Cleared 4 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

Points per level

LevelClaude Opus 5.5GPT-6.1 Terra Low
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
10.2 ptsClearedFinished early · 1 beacon left
9.2 ptsCleared
Level 3Relay vault
19.2 ptsCleared
18.8 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
10.2 ptsFinished early
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

Claude Opus 5.5

Open lateral sightlines, first reflected silhouettes and near-field planar panel placement are convincing. Missing outer chains, truncated repetitions and absent nested spherical room and emitter imagery remain the main weaknesses.

GPT-6.1 Terra Low

Deformed colored paint and a separate airborne black body establish readable interaction history. Cyan has travelled too far, framing differs substantially, and the mirror system supplies only elementary bands and oval copies. Missing recursive geometry, nested spherical imagery and emitter mapping remain the dominant weaknesses.

Score breakdown

CategoryClaude Opus 5.5GPT-6.1 Terra Low
State at 600 ms24.0/2522.0/25
Camera and placement15.0/154.0/15
Reflections55.0/12010.0/120
Materials and scale9.0/106.0/10
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 Opus 5.5

The centered coral squid has a friendly, restrained expression and a balanced radial silhouette within a cream arch. Smooth curves and soft shading give it an appealing matte finish. The mantle is more elongated than compact, the upper arms are visually ambiguous, and the two hanging tentacles read somewhat like legs. Clean execution supports a strong stylized illustration.

GPT-6.1 Terra Low

Six attached outward-facing heads, delicate scales and soft ivory shading establish an orderly decorative motif. Separate paddle-shaped bodies replace the required interlocking loops and leave no enclosed central hexagon. Surface detail provides interest, but repeated simple forms, schematic faces and limited anatomical modeling constrain the result.

Score breakdown

CategoryClaude Opus 5.5GPT-6.1 Terra Low
Task & likeness8.0/104.0/10
Anatomy & construction7.5/103.5/10
Space & placement8.0/104.5/10
Light & reflections7.5/105.5/10
Purposeful detail7.0/105.5/10
Artistry & character7.0/105.0/10
Materials & effects7.0/105.5/10
Visual integrity8.5/104.0/10

Benchmark task

Claude Opus 5.5

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

GPT-6.1 Terra Low

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 Opus 5.5

The portrait preserves the recognizable composition, dark veil, folded hands and distant landscape. Replication is limited by the elongated face and neck, conspicuous eyes and simplified smile. Hands remain connected but their rounded fingers and wrists lack convincing anatomy. Restrained colors create cohesion; shallow modeling and pervasive mottling weaken volume and painterly subtlety.

GPT-6.1 Terra Low

A recognizable, coherent portrait with purposeful facial detail, warm local volume and layered scenery. The frontal pose, enlarged face, merged hands and shallow clothing construction substantially limit replication and drawing skill. The visible successes support retaining the current assessment.

Score breakdown

CategoryClaude Opus 5.5GPT-6.1 Terra Low
Task & likeness6.5/105.0/10
Anatomy & construction5.5/104.5/10
Space & placement6.5/105.0/10
Light & reflections6.5/106.0/10
Purposeful detail6.5/105.0/10
Artistry & character6.0/105.5/10
Materials & effects7.0/105.0/10
Visual integrity7.0/106.0/10

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

Claude Opus 5.5

A lively, well-composed beach illustration with rich sunset colors, recognizable animals and appealing accessories. The sun reflection establishes a strong central focus. Clean silhouettes and small details reward inspection, though simplified animal construction, uneven contact shadows and mostly flat materials limit depth and realism.

GPT-6.1 Terra Low

A coherent sunset scene demonstrates the beach, animals, birds and reflections. Flowing silhouettes, warm color transitions and intact attachments are its strongest properties. Simplified anatomy, the turtle's elevated viewing angle and symbolic surface effects constrain drawing complexity and physical depth.

Score breakdown

CategoryClaude Opus 5.5GPT-6.1 Terra Low
Task & likeness8.5/108.0/10
Anatomy & construction7.5/105.5/10
Space & placement7.0/105.5/10
Light & reflections7.5/106.5/10
Purposeful detail7.5/106.0/10
Artistry & character8.0/105.0/10
Materials & effects6.5/105.5/10
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 Opus 5.5

This benchmark has not been assessed yet.

GPT-6.1 Terra Low

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 Opus 5.5

The masked raccoon clearly rides the dog's back, and the dog's forward paw reaches the steering grip. Expressive faces, vivid colors and sweeping wakes create an appealing illustration. Connected limbs remain schematic, as does the small steering assembly. The broad hull and flat foam weaken water contact; the glowing sun lacks a corresponding reflection or convincing cast shadows.

GPT-6.1 Terra Low

Recognizable animals, a coherent craft and sweeping wake make an appealing cartoon. Basic limb construction, weakly demonstrated raccoon seating and limited shared perspective constrain the scene. Small identifying details work well, while lighting and materials remain broadly graphic.

Score breakdown

CategoryClaude Opus 5.5GPT-6.1 Terra Low
Task & likeness8.5/106.5/10
Anatomy & construction7.5/105.0/10
Space & placement7.5/105.5/10
Light & reflections6.0/104.5/10
Purposeful detail8.5/106.0/10
Artistry & character7.0/105.0/10
Materials & effects7.0/105.0/10
Visual integrity8.0/106.0/10

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 Opus 5.5

The recognizable pelican, orderly bicycle wheels and harmonious sunset create an appealing illustration. Both legs connect to the body and reach pedals; no clear detached or inverted parts appear. Steering contact and seating support are less convincing, while the drivetrain remains schematic. Crisp outlines give a clean finish, but limited shading and flat surfaces leave the scene with modest depth.

GPT-6.1 Terra Low

A coherent coastal illustration with a distinctive pelican, controlled contours and clearly organised bicycle wheels. Visible saddle support and shaped neck and wing contours earn credit beyond basic geometric construction. Rubbery legs, unresolved pedal contacts and absent steering contact limit the riding action. Lighting and materials remain restrained and spatially shallow.

Score breakdown

CategoryClaude Opus 5.5GPT-6.1 Terra Low
Task & likeness8.5/107.0/10
Anatomy & construction8.0/105.5/10
Space & placement7.0/106.0/10
Light & reflections6.0/105.5/10
Purposeful detail8.0/106.5/10
Artistry & character7.5/106.0/10
Materials & effects6.0/106.0/10
Visual integrity8.5/106.0/10

Benchmark task

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