GPT-6.1 Terra 62.0/100Rank 9/50

STEALTHMARK · HEAD TO HEAD
All comparisons ↗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 ↘On every task, result quality and reasoning tokens are each compared with all measured models and weighed equally. Each dot is one model.
BENCHMARK BY BENCHMARK
DATASHEET
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.
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.


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.


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


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.
| Category | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| State at 600 ms | 23.0/25 | 6.0/25 |
| Camera and placement | 11.0/15 | 8.5/15 |
| Reflections | 33.0/120 | 5.5/120 |
| Materials and scale | 7.5/10 | 4.0/10 |
| Floor-damage reward | 0.0/10 | 0.0/10 |
A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.
Visual construction and creative interpretation.


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.
| Category | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| Task & likeness | 7.5/10 | 8.0/10 |
| Anatomy & construction | 6.5/10 | 5.0/10 |
| Space & placement | 6.5/10 | 6.5/10 |
| Light & reflections | 6.0/10 | 7.0/10 |
| Purposeful detail | 6.5/10 | 6.5/10 |
| Artistry & character | 6.5/10 | 5.5/10 |
| Materials & effects | 6.0/10 | 6.5/10 |
| Visual integrity | 6.0/10 | 7.5/10 |
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.
Precise visual recall and portrait reconstruction.


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.
| Category | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| Task & likeness | 5.5/10 | 1.0/10 |
| Anatomy & construction | 6.5/10 | 1.5/10 |
| Space & placement | 4.5/10 | 1.5/10 |
| Light & reflections | 6.5/10 | 1.5/10 |
| Purposeful detail | 6.0/10 | 1.0/10 |
| Artistry & character | 6.0/10 | 1.5/10 |
| Materials & effects | 6.0/10 | 1.5/10 |
| Visual integrity | 6.5/10 | 3.0/10 |
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
Creativity, perspective and visual beauty.


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.
| Category | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| Task & likeness | 8.5/10 | 6.5/10 |
| Anatomy & construction | 7.5/10 | 3.0/10 |
| Space & placement | 6.5/10 | 5.5/10 |
| Light & reflections | 5.5/10 | 6.5/10 |
| Purposeful detail | 7.5/10 | 5.0/10 |
| Artistry & character | 7.0/10 | 3.5/10 |
| Materials & effects | 6.5/10 | 3.0/10 |
| Visual integrity | 7.5/10 | 3.5/10 |
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Physical reasoning, light and visual reconstruction.


GPT-6.1 Terra
This benchmark has not been assessed yet.
Muse Spark 1.3
This benchmark has not been assessed yet.
A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.
Scene composition and interacting subjects.


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.
| Category | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| Task & likeness | 6.5/10 | 8.5/10 |
| Anatomy & construction | 5.5/10 | 6.5/10 |
| Space & placement | 6.0/10 | 7.0/10 |
| Light & reflections | 5.0/10 | 5.0/10 |
| Purposeful detail | 7.0/10 | 6.5/10 |
| Artistry & character | 6.0/10 | 5.5/10 |
| Materials & effects | 6.0/10 | 6.0/10 |
| Visual integrity | 7.0/10 | 7.5/10 |
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.
Subject construction and spatial relationships.


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.
| Category | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| Task & likeness | 7.0/10 | 8.5/10 |
| Anatomy & construction | 7.0/10 | 6.0/10 |
| Space & placement | 6.0/10 | 7.0/10 |
| Light & reflections | 5.5/10 | 6.0/10 |
| Purposeful detail | 7.0/10 | 7.0/10 |
| Artistry & character | 6.5/10 | 5.5/10 |
| Materials & effects | 5.5/10 | 6.5/10 |
| Visual integrity | 6.0/10 | 7.0/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.