GPT-6 Luna 29.8/100Rank 37/54

STEALTHMARK · HEAD TO HEAD
All comparisons ↗MiMo-V2.6-Flash leads GPT-6 Luna by 10.2 points on StealthMark, 49.3 to 39.1. It leads on 5 of 9 benchmarks and GPT-6 Luna on 4, including both games. MiMo-V2.6-Flash scores higher on Ground Truth.
See the difference ↘How many reasoning tokens a model needs for the quality it delivers.
How much Performance you get for your money.
BENCHMARK BY BENCHMARK
DATASHEET
MiMo-V2.6-Flash scores higher on StealthMark, is 1.8× cheaper per output token and runs 4.2× faster in our speed test. Both take about 1.05M tokens of context.
Full datasheets, every price and sourceGPT-6 Luna ↗MiMo-V2.6-Flash ↗
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 Luna
The schematic scene supports the paint contact order and compact paint scale. Its low, undersized main sphere and incorrectly placed wall images depart from the reference geometry. A few shrinking wall images provide limited optical organization, while absent lateral recursion and outer chains, broad sphere ribbons and isolated panel highlights leave most nested room and emitter mapping undeveloped.
MiMo-V2.6-Flash
The main sphere's scale, approximate placement and separate airborne black are supported. The colored beads do not establish the required paint history. Plausible locations for three reflected silhouettes provide limited optical credit, while missing chains, nested imagery and coherent emitter mapping dominate the assessment.
| Category | GPT-6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| State at 600 ms | 22.0/25 | 13.0/25 |
| Camera and placement | 3.5/15 | 12.0/15 |
| Reflections | 5.0/120 | 15.5/120 |
| Materials and scale | 7.0/10 | 7.5/10 |
| 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 Luna
Sixfold symmetry, pale coloring and six outward-facing heads establish the motif. However, every neck floats clear of the knot. Squared outer sections replace the required semicircular lobes, and the large stepped opening lacks a regular hexagonal contour. Repeated scales and soft shading suggest skin, but translucent crossings and doubled edges weaken the living, interwoven construction.
MiMo-V2.6-Flash
The centered rabbit has an appealing alert expression, a balanced silhouette, and a restrained technological palette. Outfit panels and orbital accents are cleanly resolved. The orb-holding paw has an ambiguous grip, the ears lack distinct angular bends, and the halo's interlocking construction is unclear. Soft shading suggests volume, but materials and spatial depth remain simplified.
| Category | GPT-6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 4.5/10 | 8.0/10 |
| Anatomy & construction | 3.5/10 | 6.5/10 |
| Space & placement | 5.5/10 | 7.0/10 |
| Light & reflections | 5.0/10 | 7.0/10 |
| Purposeful detail | 5.0/10 | 6.0/10 |
| Artistry & character | 5.0/10 | 5.5/10 |
| Materials & effects | 5.0/10 | 6.5/10 |
| Visual integrity | 4.5/10 | 8.0/10 |
GPT-6 Luna
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.
MiMo-V2.6-Flash
A small rabbit in an explorer outfit floats with a luminous orb. The scene tests character anatomy, pose and the placement of geometric forms around it.
Precise visual recall and portrait reconstruction.


GPT-6 Luna
The dark veil, crossed arms, restrained smile and layered landscape clearly evoke Mona Lisa. Clean contours and muted colors create a coherent illustration. Replication is limited by enlarged, outlined eyes, simplified facial volume, broad shoulders and indistinct overlapping hands. Gradients suggest depth, but lack the original's subtle painterly transitions.
MiMo-V2.6-Flash
The dark clothing, long hair, folded hands and hazy landscape make the reference recognizable. Replication is limited by the frontal symmetry, elongated face, wide staring eyes and downturned mouth. Both arms connect to the hands, but the overlapping palms and looplike fingers are poorly resolved. Soft facial shading provides some volume; the clothing and landscape remain broad, simplified shapes.
| Category | GPT-6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 4.5/10 | 3.0/10 |
| Anatomy & construction | 4.0/10 | 3.0/10 |
| Space & placement | 5.5/10 | 4.0/10 |
| Light & reflections | 5.0/10 | 3.0/10 |
| Purposeful detail | 5.0/10 | 4.0/10 |
| Artistry & character | 4.5/10 | 3.0/10 |
| Materials & effects | 5.0/10 | 3.5/10 |
| Visual integrity | 6.0/10 | 5.5/10 |
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 Luna
The warm sky, layered sea and framing palms create an appealing beach composition. Animals, birds, toys and reflected sunlight fulfill the brief. Human anatomy remains schematic, and simplified figures offer limited expression. Missing shadows and the dolphin's splashless jump weaken physical grounding, while clean silhouettes and readable small details support the illustration.
MiMo-V2.6-Flash
The warm sunset, aligned reflection, framing palms and playful beach animals create an appealing, coherent scene. Small toys and shells remain readable. Drawing is simplified: animals have limited volume, water uses repetitive horizontal strokes, and foreground shadows do not consistently follow the central sun. Clean execution supports a competent illustration, but depth and material rendering remain modest.
| Category | GPT-6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 7.5/10 | 7.5/10 |
| Anatomy & construction | 5.0/10 | 6.5/10 |
| Space & placement | 7.5/10 | 7.0/10 |
| Light & reflections | 5.0/10 | 6.0/10 |
| Purposeful detail | 7.0/10 | 7.0/10 |
| Artistry & character | 5.0/10 | 6.0/10 |
| Materials & effects | 6.5/10 | 6.0/10 |
| Visual integrity | 6.0/10 | 8.0/10 |
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 Luna
This benchmark has not been assessed yet.
MiMo-V2.6-Flash
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 Luna
Expressive faces, warm sunset colors and clean silhouettes create an appealing illustration. The raccoon sits on the dog's back, but the dog's grip and steering linkage remain unclear. The broad hull resembles a speedboat, and flat shading, absent sun reflections and modest water displacement limit depth and motion.
MiMo-V2.6-Flash
The raccoon riding the dog reads clearly, with expressive faces and a cheerful waterscape. The steering action is weak: no paw reaches the handlebar, which meets the dog's muzzle. The vehicle resembles a thin board with a steering post. Overlapping limbs obscure anatomy, while limited shadows, reflections and surface modeling keep the scene flat.
| Category | GPT-6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 8.0/10 | 6.5/10 |
| Anatomy & construction | 5.5/10 | 4.0/10 |
| Space & placement | 7.5/10 | 6.5/10 |
| Light & reflections | 6.0/10 | 4.5/10 |
| Purposeful detail | 7.0/10 | 5.5/10 |
| Artistry & character | 5.5/10 | 4.0/10 |
| Materials & effects | 6.5/10 | 5.5/10 |
| Visual integrity | 5.0/10 | 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.


GPT-6 Luna
The pelican’s distinctive bill and the coordinated vintage poster palette make an appealing illustration. Circular wheels, orderly spokes and clean lettering strengthen the design. Riding mechanics are less convincing: neither wing reaches the handlebars, pedal contact is ambiguous, and the drivetrain is incomplete. The wheels sit against water without a clear supporting surface. Flat lighting limits volume.
MiMo-V2.6-Flash
The pelican is immediately recognizable, with an expressive eye and prominent pouch, and the landscape provides clear framing. Clean outlines and spokes support the cheerful illustration. Both feet visibly miss the bicycle's pedal mechanism, weakening the riding action. Simplified machinery, shallow depth and loosely directional shading limit the requested masterpiece quality.
| Category | GPT-6 Luna | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 8.0/10 | 8.0/10 |
| Anatomy & construction | 5.0/10 | 5.5/10 |
| Space & placement | 6.5/10 | 7.0/10 |
| Light & reflections | 6.5/10 | 6.0/10 |
| Purposeful detail | 7.5/10 | 7.0/10 |
| Artistry & character | 6.5/10 | 6.5/10 |
| Materials & effects | 6.5/10 | 5.5/10 |
| Visual integrity | 7.0/10 | 7.5/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.