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

STEALTHMARK · HEAD TO HEAD
All comparisons ↗GPT-6.1 Terra Low leads Nemotron 3 Ultra by 24.6 points on StealthMark, 41.3 to 16.7. It leads on all 9 benchmarks. GPT-6.1 Terra Low scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.
See the difference ↘BENCHMARK BY BENCHMARK
DATASHEET
Full datasheets, every price and sourceNemotron 3 Ultra ↗
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 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.
Nemotron 3 Ultra
The candidate establishes a separate airborne black blob and partial crimson overlap, but leaves the paint interaction history and settled support unresolved. Its main silhouette, black placement and lamp projection depart substantially from the required camera geometry. A few faint reflection hints provide little support for the extensive mirror system, while the compact paint volumes are visibly disproportionate.
| Category | GPT-6.1 Terra Low | Nemotron 3 Ultra |
|---|---|---|
| State at 600 ms | 22.0/25 | 2.0/25 |
| Camera and placement | 4.0/15 | 3.5/15 |
| Reflections | 10.0/120 | 4.5/120 |
| Materials and scale | 6.0/10 | 3.0/10 |
| 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 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.
Nemotron 3 Ultra
An endearing mechanical creature is clearly framed, with expressive amber eyes and readable segmented arms. The shell resembles layered green plates more than a deep coiled spiral. Detached-looking construction, absent working contacts and patchy rendering leave the central assembly action substantially unresolved.
| Category | GPT-6.1 Terra Low | Nemotron 3 Ultra |
|---|---|---|
| Task & likeness | 4.0/10 | 4.0/10 |
| Anatomy & construction | 3.5/10 | 4.0/10 |
| Space & placement | 4.5/10 | 5.5/10 |
| Light & reflections | 5.5/10 | 5.0/10 |
| Purposeful detail | 5.5/10 | 4.0/10 |
| Artistry & character | 5.0/10 | 3.0/10 |
| Materials & effects | 5.5/10 | 4.0/10 |
| Visual integrity | 4.0/10 | 4.5/10 |
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.
Nemotron 3 Ultra
A hovering mechanical nautilus tests spiral construction, connected mechanical forms and contrasting metal and illuminated surfaces.
Precise visual recall and portrait reconstruction.


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.
Nemotron 3 Ultra
The centered silhouette provides basic organization, but multicolored mottling and geometric overlays leave the portrait unresolved. No readable face, crossed hands, clothing or landscape establishes Mona Lisa replication. Texture and transparency offer limited visual effects without coherent anatomy, lighting or material distinctions.
| Category | GPT-6.1 Terra Low | Nemotron 3 Ultra |
|---|---|---|
| Task & likeness | 5.0/10 | 0.5/10 |
| Anatomy & construction | 4.5/10 | 0.0/10 |
| Space & placement | 5.0/10 | 1.0/10 |
| Light & reflections | 6.0/10 | 0.5/10 |
| Purposeful detail | 5.0/10 | 0.5/10 |
| Artistry & character | 5.5/10 | 1.5/10 |
| Materials & effects | 5.0/10 | 0.0/10 |
| Visual integrity | 6.0/10 | 0.5/10 |
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 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.
Nemotron 3 Ultra
A recognizable beach illustration with appealing warm-cool contrast, readable layers and mostly clean shapes. Unresolved seat construction, schematic animals and broad geometric foliage give it an elementary finish. Weakly coordinated reflections and limited material differentiation further constrain depth and atmosphere.
| Category | GPT-6.1 Terra Low | Nemotron 3 Ultra |
|---|---|---|
| Task & likeness | 8.0/10 | 6.5/10 |
| Anatomy & construction | 5.5/10 | 3.0/10 |
| Space & placement | 5.5/10 | 5.0/10 |
| Light & reflections | 6.5/10 | 1.5/10 |
| Purposeful detail | 6.0/10 | 4.5/10 |
| Artistry & character | 5.0/10 | 3.0/10 |
| Materials & effects | 5.5/10 | 2.5/10 |
| Visual integrity | 7.5/10 | 6.5/10 |
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 Low
This benchmark has not been assessed yet.
Nemotron 3 Ultra
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 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.
Nemotron 3 Ultra
The masked raccoon, dog and orange craft make the scene recognizable, with an appealing sunset palette. Overlapping bodies obscure the riding relationship, and the dog's connection to the controls remains unresolved. Weak water displacement, inconsistent shading and visible shape artifacts limit the finish. Ambiguous attachments do not establish detached limbs or inverted anatomy.
| Category | GPT-6.1 Terra Low | Nemotron 3 Ultra |
|---|---|---|
| Task & likeness | 6.5/10 | 3.5/10 |
| Anatomy & construction | 5.0/10 | 1.5/10 |
| Space & placement | 5.5/10 | 4.5/10 |
| Light & reflections | 4.5/10 | 2.0/10 |
| Purposeful detail | 6.0/10 | 3.5/10 |
| Artistry & character | 5.0/10 | 1.5/10 |
| Materials & effects | 5.0/10 | 3.0/10 |
| Visual integrity | 6.0/10 | 2.0/10 |
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 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.
Nemotron 3 Ultra
A recognizable, playful pelican dominates a readable bicycle scene. Its bill and silhouette succeed, but feet below the pedals and confused drivetrain connections weaken the riding action. Local material modeling adds interest; overlapping contours, repetitive detail and inconsistent shadows leave the illustration basic and uneven.
| Category | GPT-6.1 Terra Low | Nemotron 3 Ultra |
|---|---|---|
| Task & likeness | 7.0/10 | 4.0/10 |
| Anatomy & construction | 5.5/10 | 3.5/10 |
| Space & placement | 6.0/10 | 3.5/10 |
| Light & reflections | 5.5/10 | 4.0/10 |
| Purposeful detail | 6.5/10 | 5.5/10 |
| Artistry & character | 6.0/10 | 4.0/10 |
| Materials & effects | 6.0/10 | 6.0/10 |
| Visual integrity | 6.0/10 | 3.0/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.