Gemma 4 26B A4B 4.1/100Rank 50/51

STEALTHMARK · HEAD TO HEAD
All comparisons ↗GPT-6.1 Terra Low leads Gemma 4 26B A4B by 24.8 points on StealthMark, 41.3 to 16.5. It leads on 8 of 9 benchmarks, including both games, and Gemma 4 26B A4B on 1. 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 sourceGemma 4 26B A4B ↗
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 ↗


Gemma 4 26B A4B
Separate airborne black and contact-compatible paint flattening earn partial state credit. Settlement, adhesion and differentiated paint transport remain unresolved. The enlarged, low sphere and thin lamp strip substantially depart from the required camera, while the defining mirror structure is missing. Weak material appearance and oversized black paint limit material credit. The retained base total is 18/170; the floor-damage reward is 0, giving 18/180.
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.
| Category | Gemma 4 26B A4B | GPT-6.1 Terra Low |
|---|---|---|
| State at 600 ms | 10.0/25 | 22.0/25 |
| Camera and placement | 2.0/15 | 4.0/15 |
| Reflections | 0.0/120 | 10.0/120 |
| Materials and scale | 2.5/10 | 6.0/10 |
| 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.


Gemma 4 26B A4B
An appealing, readable sparkle-creature with luminous colour and expressive eyes. Simple geometric construction limits sophistication, while sharp body points, ambiguous hand contact and a minimally resolved jar weaken the requested soft, plump character and treasure-presenting pose.
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.
| Category | Gemma 4 26B A4B | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 5.5/10 | 4.0/10 |
| Anatomy & construction | 4.5/10 | 3.5/10 |
| Space & placement | 6.0/10 | 4.5/10 |
| Light & reflections | 6.0/10 | 5.5/10 |
| Purposeful detail | 5.5/10 | 5.5/10 |
| Artistry & character | 4.0/10 | 5.0/10 |
| Materials & effects | 6.0/10 | 5.5/10 |
| Visual integrity | 7.0/10 | 4.0/10 |
Gemma 4 26B A4B
A small luminous creature proudly holding an empty glass jar tests expression, transparent materials and the balance of character and prop.
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.
Precise visual recall and portrait reconstruction.


Gemma 4 26B A4B
The centered dark-haired portrait provides a loose reference cue, but its elongated, nearly featureless face and undifferentiated torso fall far short of replication. Crossed hands, the subtle smile, clothing structure and landscape are unresolved. Clean silhouettes and soft gradients provide limited coherence.
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.
| Category | Gemma 4 26B A4B | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 0.5/10 | 5.0/10 |
| Anatomy & construction | 2.0/10 | 4.5/10 |
| Space & placement | 1.0/10 | 5.0/10 |
| Light & reflections | 2.0/10 | 6.0/10 |
| Purposeful detail | 1.0/10 | 5.0/10 |
| Artistry & character | 2.0/10 | 5.5/10 |
| Materials & effects | 1.0/10 | 5.0/10 |
| Visual integrity | 4.5/10 | 6.0/10 |
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
Creativity, perspective and visual beauty.


Gemma 4 26B A4B
A clean, balanced sunset scene demonstrates the beach, birds and a centered reflection. Animals and play receive only minimal treatment. Coherent layers and controlled gradients support readability, but unresolved aquatic anatomy, sparse details and weak surface modeling keep the drawing basic.
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.
| Category | Gemma 4 26B A4B | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 3.5/10 | 8.0/10 |
| Anatomy & construction | 2.0/10 | 5.5/10 |
| Space & placement | 3.5/10 | 5.5/10 |
| Light & reflections | 5.0/10 | 6.5/10 |
| Purposeful detail | 1.0/10 | 6.0/10 |
| Artistry & character | 1.5/10 | 5.0/10 |
| Materials & effects | 2.0/10 | 5.5/10 |
| Visual integrity | 6.0/10 | 7.5/10 |
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Physical reasoning, light and visual reconstruction.


Gemma 4 26B A4B
This benchmark has not been assessed yet.
GPT-6.1 Terra Low
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.


Gemma 4 26B A4B
The animal stack is recognizable, and clean silhouettes support a basic illustration. Steering is not depicted, while the craft's construction and water contact remain unresolved. Sparse anatomical and material detail limit the finish. The sky gradient and glow provide atmospheric lighting, but the subjects lack corresponding modeling.
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.
| Category | Gemma 4 26B A4B | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 2.5/10 | 6.5/10 |
| Anatomy & construction | 2.5/10 | 5.0/10 |
| Space & placement | 4.0/10 | 5.5/10 |
| Light & reflections | 3.5/10 | 4.5/10 |
| Purposeful detail | 2.5/10 | 6.0/10 |
| Artistry & character | 3.0/10 | 5.0/10 |
| Materials & effects | 2.0/10 | 5.0/10 |
| Visual integrity | 7.0/10 | 6.0/10 |
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.


Gemma 4 26B A4B
A clean, balanced icon suggests a pelican riding a bicycle. Continuous contours and restrained colors support its finish, but the abbreviated bill, undifferentiated body, unresolved riding contacts and incomplete bicycle mechanism limit likeness and construction. Sparse detail and flat lighting keep the drawing basic despite its clarity.
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.
| Category | Gemma 4 26B A4B | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 3.0/10 | 7.0/10 |
| Anatomy & construction | 3.0/10 | 5.5/10 |
| Space & placement | 5.0/10 | 6.0/10 |
| Light & reflections | 3.0/10 | 5.5/10 |
| Purposeful detail | 3.0/10 | 6.5/10 |
| Artistry & character | 2.5/10 | 6.0/10 |
| Materials & effects | 2.5/10 | 6.0/10 |
| Visual integrity | 5.0/10 | 6.0/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.