GLM-5.3 43.6/100Rank 25/54

STEALTHMARK · HEAD TO HEAD
All comparisons ↗GLM-5.3 leads GPT-6 Luna by 13.8 points on StealthMark, 52.9 to 39.1. It leads on 7 of 9 benchmarks, including Foresight, and GPT-6 Luna on 2, including Latch. GLM-5.3 scores higher on Newton's Mirror, with its largest category advantage in reflections.
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
GLM-5.3 scores higher on StealthMark. GPT-6 Luna is 8.8× cheaper per output token and runs 1.5× faster in our speed test. Both take about 1M tokens of context.
Full datasheets, every price and sourceGLM-5.3 ↗GPT-6 Luna ↗
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 ↗


GLM-5.3
The central sphere, isolated airborne black blob and crimson leading-end placement are well established. Recent cyan contact remains only partially demonstrated. The dominant weakness is optical: sparse shaded sphere rows, missing outer chains and diffuse highlights replace extensive mirror repetition and curved nested imagery.
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.
| Category | GLM-5.3 | GPT-6 Luna |
|---|---|---|
| State at 600 ms | 22.5/25 | 22.0/25 |
| Camera and placement | 13.0/15 | 3.5/15 |
| Reflections | 37.0/120 | 5.0/120 |
| Materials and scale | 7.0/10 | 7.0/10 |
| 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.


GLM-5.3
A luminous organic creature meets a geometric reflection in a carefully framed oval mirror. Shared glowing cores and fingertip contact make the introspective symbolism clear. Gold, cream and blue establish a controlled hierarchy. The creature’s lower anatomy and shoulder transition remain loosely defined, while ground contact and reflected depth are mostly symbolic. Elegant vector illustration rather than photographic rendering.
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.
| Category | GLM-5.3 | GPT-6 Luna |
|---|---|---|
| Task & likeness | 9.0/10 | 4.5/10 |
| Anatomy & construction | 7.0/10 | 3.5/10 |
| Space & placement | 7.0/10 | 5.5/10 |
| Light & reflections | 8.0/10 | 5.0/10 |
| Purposeful detail | 8.0/10 | 5.0/10 |
| Artistry & character | 7.0/10 | 5.0/10 |
| Materials & effects | 7.5/10 | 5.0/10 |
| Visual integrity | 8.0/10 | 4.5/10 |
GLM-5.3
An imagined creature encounters its reflection. The scene tests original character design, visual self-interpretation and the relationship between a subject and its reflected image.
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.
Precise visual recall and portrait reconstruction.


GLM-5.3
A recognizable, coherent interpretation with purposeful facial accents, readable shading and intact principal attachments. These demonstrated strengths warrant modest upward calibration. Frontal seating, distorted proportions, schematic hands and uniform surfaces still limit likeness, anatomy, depth and artistic refinement.
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.
| Category | GLM-5.3 | GPT-6 Luna |
|---|---|---|
| Task & likeness | 4.5/10 | 4.5/10 |
| Anatomy & construction | 4.5/10 | 4.0/10 |
| Space & placement | 4.5/10 | 5.5/10 |
| Light & reflections | 6.0/10 | 5.0/10 |
| Purposeful detail | 5.0/10 | 5.0/10 |
| Artistry & character | 5.0/10 | 4.5/10 |
| Materials & effects | 5.0/10 | 5.0/10 |
| Visual integrity | 6.0/10 | 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.


GLM-5.3
A coherent beach illustration with a clear sunset, playful subjects and purposeful small details. Varied silhouettes and broken reflections strengthen its composition. Basic human anatomy, shallow foreground construction and limited material differentiation constrain the result. The kite line reaches the smaller figure rather than requiring a grip from the nearby animal.
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.
| Category | GLM-5.3 | GPT-6 Luna |
|---|---|---|
| Task & likeness | 8.5/10 | 7.5/10 |
| Anatomy & construction | 5.5/10 | 5.0/10 |
| Space & placement | 6.0/10 | 7.5/10 |
| Light & reflections | 7.0/10 | 5.0/10 |
| Purposeful detail | 7.0/10 | 7.0/10 |
| Artistry & character | 5.5/10 | 5.0/10 |
| Materials & effects | 6.5/10 | 6.5/10 |
| Visual integrity | 7.0/10 | 6.0/10 |
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Physical reasoning, light and visual reconstruction.


GLM-5.3
This benchmark has not been assessed yet.
GPT-6 Luna
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.


GLM-5.3
A coherent sunset illustration with readable steering, expressive accessories and effective translucent water effects. Its strongest physical lighting evidence is the aligned sun reflection. The raccoon's seated support remains unresolved, while simplified joints and limited viewpoint integration constrain construction and artistry.
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.
| Category | GLM-5.3 | GPT-6 Luna |
|---|---|---|
| Task & likeness | 7.0/10 | 8.0/10 |
| Anatomy & construction | 6.0/10 | 5.5/10 |
| Space & placement | 6.0/10 | 7.5/10 |
| Light & reflections | 7.0/10 | 6.0/10 |
| Purposeful detail | 7.5/10 | 7.0/10 |
| Artistry & character | 6.0/10 | 5.5/10 |
| Materials & effects | 7.5/10 | 6.5/10 |
| Visual integrity | 5.5/10 | 5.0/10 |
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.


GLM-5.3
A coherent coastal illustration with a distinctive pelican silhouette, expressive flowing shapes and substantial bicycle detail. Feet meet plausible pedal platforms, but steering contact remains unresolved. Simplified leg articulation, modest depth and approximate directional lighting limit physical construction. The apparent neck opening is ambiguous rather than a verified break.
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.
| Category | GLM-5.3 | GPT-6 Luna |
|---|---|---|
| Task & likeness | 7.0/10 | 8.0/10 |
| Anatomy & construction | 5.0/10 | 5.0/10 |
| Space & placement | 6.0/10 | 6.5/10 |
| Light & reflections | 6.0/10 | 6.5/10 |
| Purposeful detail | 7.5/10 | 7.5/10 |
| Artistry & character | 6.0/10 | 6.5/10 |
| Materials & effects | 6.5/10 | 6.5/10 |
| Visual integrity | 6.0/10 | 7.0/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.