STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6.1 Terra vs Muse Spark 1.3

GPT-6.1 Terra leads Muse Spark 1.3 by 20.6 points on StealthMark, 60.4 to 39.8. It leads on 6 of 9 benchmarks, including Latch, and Muse Spark 1.3 on 3, including Foresight. GPT-6.1 Terra scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

60.4/100Overall rank 9/54
39.8/100Overall rank 35/54

General Intelligence

58.0/100
38.3/100

Visual Intelligence

64.9/100
42.3/100

Reasoning efficiency

On every task, result quality and reasoning tokens are each compared with all measured models and weighed equally. Each dot is one model.

Single-step reasoning Result quality weighed against reasoning tokens on a single problem

Multi-step reasoning Result quality weighed against reasoning tokens across connected steps, as in agentic workflows

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6.1 Terra
  • Muse Spark 1.3
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-6.1 Terra scores higher on StealthMark. Muse Spark 1.3 is 18% cheaper per output token. Both take about 1.05M tokens of context.

  • GPT-6.1 Terra
  • Muse Spark 1.3
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6.1 Terra: $5$1 inputMuse Spark 1.3: $4.2518% cheaper$1.25 input
Context windowTokens per request, max output below
GPT-6.1 Terra: 1.05MTied128K max outputMuse Spark 1.3: 1MTied
Output speedTokens per second, our measurement
GPT-6.1 Terra: Not measuredMuse Spark 1.3: 321tokens/s
Developer
OpenAIMeta
Released
26 Oct 20262 Sep 2026
Origin
United StatesBoth
Input → output
Text, image → textText, image, video, audio, PDF → text

Full datasheets, every price and sourceGPT-6.1 Terra ↗Muse Spark 1.3 ↗

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-6.1 Terra 62.0/100Rank 9/50

Survived 2 of 3
Foresight: complete playing field
Level 315 ptsTurn 20 / 20

Muse Spark 1.3 64.3/100Rank 6/50

Survived 2 of 3
Foresight: complete playing field
Level 311 ptsTurn 17 / 20

Points per level

LevelGPT-6.1 TerraMuse Spark 1.3
Level 1Second Thoughts
21 ptsSurvived
26 ptsSurvived
Level 2Pressure Pot
9 ptsOut of lives
10 ptsSurvived
Level 3Hide or Flight
15 ptsSurvived
11 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-6.1 Terra 77.7/100Rank 12/51

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

Muse Spark 1.3 72.4/100Rank 28/513 of 5 levels

3 of 5 played
Latch: complete playing field
Level 318.8 ptsTurn 32 / 36

Points per level

LevelGPT-6.1 TerraMuse Spark 1.3
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
9.8 ptsCleared
Level 3Relay vault
19.2 ptsCleared
18.8 ptsCleared
Level 4Passing bay
17.8 ptsClearedFinished early · 3 beacons left
Pending
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-6.1 Terra

The sphere, airborne black and first reflected silhouettes preserve important geometry within the portrait frame. Paint deformation, contact order and forward transport are supported, with a small crimson endpoint overshoot. Major optical omissions dominate: short finite reflection sequences and smooth bands replace extensive, spatially ordered mirror imagery. Dark gloss and crisp upper emitter shapes provide partial material credit.

Muse Spark 1.3

The paint state is incorrectly and poorly drawn, despite a recognizable sphere-and-paint setup. The oversized sphere, oversized compact paint bodies, and blurred wall and floor images further limit the result. Isolated reflection cues provide very little support for the required repeated virtual rooms, nested spherical imagery or emitter mapping.

Score breakdown

CategoryGPT-6.1 TerraMuse Spark 1.3
State at 600 ms23.0/256.0/25
Camera and placement11.0/158.5/15
Reflections33.0/1205.5/120
Materials and scale7.5/104.0/10
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-6.1 Terra

A balanced serpent emblem with six attached outward heads, delicate scales and softly rounded bodies. Its compact silhouette reads clearly, but central routing does not establish every alternating crossing or crisp inward corner. Repetitive texture, limited facial anatomy and weak contact shadows constrain its organic character.

Muse Spark 1.3

The luminous creature and geometric mirror counterpart communicate self-recognition through a coherent palette and expressive eyes. The transformed reflection is purposeful. Simple oval anatomy, ambiguous reaching-arm construction, shallow spatial staging and limited illumination of nearby surfaces keep the illustration below exceptional execution.

Score breakdown

CategoryGPT-6.1 TerraMuse Spark 1.3
Task & likeness7.5/108.0/10
Anatomy & construction6.5/105.0/10
Space & placement6.5/106.5/10
Light & reflections6.0/107.0/10
Purposeful detail6.5/106.5/10
Artistry & character6.5/105.5/10
Materials & effects6.0/106.5/10
Visual integrity6.0/107.5/10

Benchmark task

GPT-6.1 Terra

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.

Muse Spark 1.3

An imagined creature encounters its reflection. The scene tests original character design, visual self-interpretation and the relationship between a subject and its reflected image.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

GPT-6.1 Terra

A recognizable interpretation with developed facial shading, shaped sleeve folds and purposeful small features. These strengths support modest upward calibration, while the frontal torso, elongated proportions, schematic finger joints and unresolved seated support keep replication and construction uneven.

Muse Spark 1.3

Dark hair, a restrained smile and overlapping hands suggest Mona Lisa, but replication is weak. The face is markedly elongated, the hands are oval pads with faint finger strokes, and the atmospheric landscape is absent. Soft gradients provide basic volume, while the frontal symmetry, shallow space and sparse clothing detail limit the portrait’s drawing quality.

Score breakdown

CategoryGPT-6.1 TerraMuse Spark 1.3
Task & likeness5.5/101.0/10
Anatomy & construction6.5/101.5/10
Space & placement4.5/101.5/10
Light & reflections6.5/101.5/10
Purposeful detail6.0/101.0/10
Artistry & character6.0/101.5/10
Materials & effects6.0/101.5/10
Visual integrity6.5/103.0/10

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-6.1 Terra

A coherent sunset illustration with clear prompt fulfillment, controlled framing and varied, purposeful small details. Simplified joints, frontal staging, flattened animal forms and weakly directional shadows limit its anatomical, spatial and physical sophistication.

Muse Spark 1.3

The warm sunset, framing palms and colorful beach accessories create an appealing scene with the requested animals, birds and reflections. Construction remains schematic: the raised hand misses the kite string, and a doglike silhouette hangs above the water without clear support. The sun reflection establishes a focal path, but shadows and materials lack depth. An unexplained horizontal bar crosses the sun.

Score breakdown

CategoryGPT-6.1 TerraMuse Spark 1.3
Task & likeness8.5/106.5/10
Anatomy & construction7.5/103.0/10
Space & placement6.5/105.5/10
Light & reflections5.5/106.5/10
Purposeful detail7.5/105.0/10
Artistry & character7.0/103.5/10
Materials & effects6.5/103.0/10
Visual integrity7.5/103.5/10

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-6.1 Terra

This benchmark has not been assessed yet.

Muse Spark 1.3

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-6.1 Terra

A coherent cartoon with expressive animals, readable steering and a clear wake. Fine facial and hull details reward inspection. The main limits are the boatlike craft, simplified joints, weakly braced frontal raccoon and minimal directional lighting or material depth.

Muse Spark 1.3

The raccoon clearly rides on the dog's back, and the dog's paws reach the jet ski controls. Expressive faces and bright colors make the scene appealing. Simplified joints, crowded steering geometry and shallow hull perspective limit construction. The sun has no corresponding water reflection, and the splash shapes convey speed more clearly than convincing displacement.

Score breakdown

CategoryGPT-6.1 TerraMuse Spark 1.3
Task & likeness6.5/108.5/10
Anatomy & construction5.5/106.5/10
Space & placement6.0/107.0/10
Light & reflections5.0/105.0/10
Purposeful detail7.0/106.5/10
Artistry & character6.0/105.5/10
Materials & effects6.0/106.0/10
Visual integrity7.0/107.5/10

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-6.1 Terra

A coherent pelican cyclist with expressive proportions, purposeful feather detail and developed bicycle machinery. Continuous body contours, aligned wheels and readable pedal contacts support the scene. Simplified articulation, shallow modelling and an unresolved steering connection limit construction and placement.

Muse Spark 1.3

The pelican and bicycle are immediately recognizable, with an expressive face, bold bill and cheerful composition. Both legs connect to the body and reach pedal-like supports, but articulation, saddle support and wing contact with the handlebar remain unclear. Wheel alignment and layering are coherent. Simple landscape shapes, generic shadows and limited material variation constrain the finish.

Score breakdown

CategoryGPT-6.1 TerraMuse Spark 1.3
Task & likeness7.0/108.5/10
Anatomy & construction7.0/106.0/10
Space & placement6.0/107.0/10
Light & reflections5.5/106.0/10
Purposeful detail7.0/107.0/10
Artistry & character6.5/105.5/10
Materials & effects5.5/106.5/10
Visual integrity6.0/107.0/10

Benchmark task

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