GPT-6.1 Terra 62.0/100Rank 9/50

STEALTHMARK · HEAD TO HEAD
All comparisons ↗GPT-6.1 Terra leads Kolibri-1 by 46.8 points on StealthMark, 60.4 to 13.6. It leads on all 7 benchmarks with results for both. 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
Both take about 1.05M tokens of context.
Full datasheets, every price and sourceGPT-6.1 Terra ↗Kolibri-1 ↗
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.
Kolibri-1
A segmented gray perimeter surrounds a black field containing one large, low-positioned gray sphere and two small colored circles. Rounded volume and restrained paint scale earn partial material credit. The image does not demonstrate the required optical structure, while paint history, airborne black and settled support remain largely unresolved.
| Category | GPT-6.1 Terra | Kolibri-1 |
|---|---|---|
| State at 600 ms | 23.0/25 | 9.5/25 |
| Camera and placement | 11.0/15 | 1.5/15 |
| Reflections | 33.0/120 | 0.0/120 |
| Materials and scale | 7.5/10 | 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
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.
Kolibri-1
A restrained ivory, teal and green palette gives the image simple graphic coherence. Execution remains rudimentary: detached oval wings, ambiguous central anatomy and unclear feeding contact prevent a convincing hummingbird scene. The requested feather structure, botanical detail, lighting and enclosing arch are largely unresolved.
| Category | GPT-6.1 Terra | Kolibri-1 |
|---|---|---|
| Task & likeness | 7.5/10 | 2.5/10 |
| Anatomy & construction | 6.5/10 | 2.0/10 |
| Space & placement | 6.5/10 | 3.0/10 |
| Light & reflections | 6.0/10 | 2.0/10 |
| Purposeful detail | 6.5/10 | 1.5/10 |
| Artistry & character | 6.5/10 | 1.5/10 |
| Materials & effects | 6.0/10 | 2.0/10 |
| Visual integrity | 6.0/10 | 5.5/10 |
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.
Kolibri-1
A jewel-coloured hummingbird hovering in flight tests avian anatomy, delicate structure and iridescent surface detail.
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.
Kolibri-1
The candidate offers a clean, highly simplified frontal portrait with warm skin and dark hair. Its oversized oval face, schematic features and unresolved body provide little Mona Lisa likeness. Missing crossed hands, clothing detail and landscape remove essential parts of the original composition; smooth gradients supply only limited volume.
| Category | GPT-6.1 Terra | Kolibri-1 |
|---|---|---|
| Task & likeness | 5.5/10 | 0.5/10 |
| Anatomy & construction | 6.5/10 | 0.5/10 |
| Space & placement | 4.5/10 | 0.0/10 |
| Light & reflections | 6.5/10 | 0.0/10 |
| Purposeful detail | 6.0/10 | 0.0/10 |
| Artistry & character | 6.0/10 | 0.5/10 |
| Materials & effects | 6.0/10 | 0.5/10 |
| Visual integrity | 6.5/10 | 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
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.
Kolibri-1
A recognizable sunset beach has an appealing purple-orange gradient and clean geometric edges. Birds and animals remain unresolved, terrain obscures the relationship between shore and water, and reflections are absent. Sparse detail, flat materials and limited activity keep the drawing elementary despite its tidy rendering.
| Category | GPT-6.1 Terra | Kolibri-1 |
|---|---|---|
| Task & likeness | 8.5/10 | 2.5/10 |
| Anatomy & construction | 7.5/10 | 0.5/10 |
| Space & placement | 6.5/10 | 3.0/10 |
| Light & reflections | 5.5/10 | 1.0/10 |
| Purposeful detail | 7.5/10 | 0.5/10 |
| Artistry & character | 7.0/10 | 1.0/10 |
| Materials & effects | 6.5/10 | 0.5/10 |
| Visual integrity | 7.5/10 | 3.0/10 |
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.
Kolibri-1
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.
Kolibri-1
Clean shapes and a readable coral platform provide basic graphic clarity, but the animal construction remains fragmented. A recognizable raccoon riding the dog's back, connected steering and convincing water contact are not demonstrated. Sparse detail, flat subjects and absent movement effects support retaining the baseline category assessments.
| Category | GPT-6.1 Terra | Kolibri-1 |
|---|---|---|
| Task & likeness | 6.5/10 | 1.5/10 |
| Anatomy & construction | 5.5/10 | 1.0/10 |
| Space & placement | 6.0/10 | 1.0/10 |
| Light & reflections | 5.0/10 | 0.0/10 |
| Purposeful detail | 7.0/10 | 0.5/10 |
| Artistry & character | 6.0/10 | 0.5/10 |
| Materials & effects | 6.0/10 | 0.5/10 |
| Visual integrity | 7.0/10 | 3.5/10 |
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.
Kolibri-1
Clean shapes and aligned wheels establish a readable schematic scene. Pelican likeness, riding support and bicycle mechanics remain substantially unresolved. Sparse detail and flat surfaces limit expression and volume. Strong edge and fill integrity is a separate success and does not repair the construction.
| Category | GPT-6.1 Terra | Kolibri-1 |
|---|---|---|
| Task & likeness | 7.0/10 | 1.5/10 |
| Anatomy & construction | 7.0/10 | 1.5/10 |
| Space & placement | 6.0/10 | 1.5/10 |
| Light & reflections | 5.5/10 | 3.0/10 |
| Purposeful detail | 7.0/10 | 1.5/10 |
| Artistry & character | 6.5/10 | 1.0/10 |
| Materials & effects | 5.5/10 | 1.0/10 |
| Visual integrity | 6.0/10 | 3.5/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.