GPT-6 Sol 30.4/100Rank 33/54

STEALTHMARK · HEAD TO HEAD
All comparisons ↗GPT-6 Sol leads MiMo-V2.6-Flash by 2.7 points on StealthMark, 52.0 to 49.3. It leads on 7 of 9 benchmarks, including both games, and MiMo-V2.6-Flash on 2. GPT-6 Sol scores higher on Raccoon, with its largest category advantage in anatomy & construction.
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
GPT-6 Sol scores higher on StealthMark. MiMo-V2.6-Flash is 36× cheaper per output token and runs 6× faster in our speed test. Both take about 1.05M tokens of context.
Full datasheets, every price and sourceGPT-6 Sol ↗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 Sol
The centered sphere, separate airborne black form and color ordering support scene recognition. Rounded shading and curved rims provide readable volume and gloss. Shrinking side images, a floor counterpart and curved lamp highlights provide isolated reflection cues, but broad bands and sparse repetitions leave nested room imagery, outer chains and ordered emitter mapping unsupported. Vertical framing departs from the prescribed view, while paint contact, transport and solid-metal appearance remain weak or uncertain.
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 Sol | MiMo-V2.6-Flash |
|---|---|---|
| State at 600 ms | 19.0/25 | 13.0/25 |
| Camera and placement | 12.0/15 | 12.0/15 |
| Reflections | 8.0/120 | 15.5/120 |
| Materials and scale | 6.5/10 | 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 Sol
Six evenly spaced lobes, small outward-facing heads and a regular hexagonal opening make the motif immediately readable. The central angular band merges several intersections, weakening the alternating weave. Pale shading gives modest volume, but scales are sparse and repetitive, crossing shadows are weak, and the heads have limited anatomical definition.
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 Sol | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 7.5/10 | 8.0/10 |
| Anatomy & construction | 6.5/10 | 6.5/10 |
| Space & placement | 6.5/10 | 7.0/10 |
| Light & reflections | 6.0/10 | 7.0/10 |
| Purposeful detail | 6.5/10 | 6.0/10 |
| Artistry & character | 7.0/10 | 5.5/10 |
| Materials & effects | 5.5/10 | 6.5/10 |
| Visual integrity | 6.0/10 | 8.0/10 |
GPT-6 Sol
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 Sol
A recognizable, coherent simplification with rounded facial shading, an asymmetric veil and readable forearm overlap. Selective eye, neckline, hair and bridge details enrich the broad shapes. The frontal pose, oversized face, schematic hands and limited fabric construction constrain replication and drawing complexity.
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 Sol | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 5.0/10 | 3.0/10 |
| Anatomy & construction | 5.0/10 | 3.0/10 |
| Space & placement | 5.0/10 | 4.0/10 |
| Light & reflections | 6.0/10 | 3.0/10 |
| Purposeful detail | 4.5/10 | 4.0/10 |
| Artistry & character | 5.5/10 | 3.0/10 |
| Materials & effects | 5.5/10 | 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 Sol
A coherent sunset illustration with clear prompt fulfilment, varied readable details and controlled atmospheric colour. Connected animal silhouettes and supported equipment withstand inspection. Simplified anatomy, ambiguous animal depth, schematic reflections and weakly directional shadows constrain its physical sophistication.
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 Sol | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 8.5/10 | 7.5/10 |
| Anatomy & construction | 6.0/10 | 6.5/10 |
| Space & placement | 6.0/10 | 7.0/10 |
| Light & reflections | 6.0/10 | 6.0/10 |
| Purposeful detail | 7.5/10 | 7.0/10 |
| Artistry & character | 6.5/10 | 6.0/10 |
| Materials & effects | 6.5/10 | 6.0/10 |
| Visual integrity | 7.5/10 | 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 Sol
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 Sol
The raccoon rides the dog's back, and the dog's connected foreleg reaches the steering grip. Expressive faces, a cohesive palette and sweeping wake make an appealing illustration. Vehicle construction and seating remain simplified; broad splash ribbons convey speed more convincingly than physical displacement. The sun has little corresponding reflection or effect on the subjects.
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 Sol | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 7.5/10 | 6.5/10 |
| Anatomy & construction | 6.5/10 | 4.0/10 |
| Space & placement | 7.5/10 | 6.5/10 |
| Light & reflections | 6.0/10 | 4.5/10 |
| Purposeful detail | 7.5/10 | 5.5/10 |
| Artistry & character | 6.5/10 | 4.0/10 |
| Materials & effects | 7.5/10 | 5.5/10 |
| Visual integrity | 8.0/10 | 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 Sol
The pelican reads clearly, with an expressive face, generous bill and appealing pastel composition. Spokes, basket weave and feather contours are carefully organized. Both legs connect to the body, though joint definition and pedal contacts are simplified. Consistent wheel placement and a ground shadow establish support; restrained shading gives limited 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 Sol | MiMo-V2.6-Flash |
|---|---|---|
| Task & likeness | 9.0/10 | 8.0/10 |
| Anatomy & construction | 7.5/10 | 5.5/10 |
| Space & placement | 8.0/10 | 7.0/10 |
| Light & reflections | 7.0/10 | 6.0/10 |
| Purposeful detail | 8.0/10 | 7.0/10 |
| Artistry & character | 8.5/10 | 6.5/10 |
| Materials & effects | 7.0/10 | 5.5/10 |
| Visual integrity | 8.5/10 | 7.5/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.