STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GLM-5.3 vs Step 5 Preview

GLM-5.3 leads Step 5 Preview by 6.1 points on StealthMark, 45.1 to 39.0. It leads on 6 of 9 benchmarks, including Foresight, and Step 5 Preview on 3, including Latch. GLM-5.3 scores higher on Beach, with its largest category advantage in anatomy & construction.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

45.1/100Overall rank 27/53
39.0/100Overall rank 36/53

General Intelligence

37.6/100
37.1/100

Visual Intelligence

57.2/100
41.9/100

Reasoning efficiency

On every task, result quality and reasoning tokens are each compared with all measured models and weighed equally. Each dot is one model.

Single-step reasoning Result quality weighed against reasoning tokens on a single problem

Multi-step reasoning Result quality weighed against reasoning tokens across connected steps, as in agentic workflows

  • GLM-5.3

Open or local

Open modelGLM-5.3 License

BENCHMARK BY BENCHMARK

Where each model leads

  • GLM-5.3
  • Step 5 Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1M tokens of context.

  • GLM-5.3
  • Step 5 Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
GLM-5.3: $4.40$1.40 inputStep 5 Preview: No list price
Context windowTokens per request, max output below
GLM-5.3: 1MTied128K max outputStep 5 Preview: 1MTied
Output speedTokens per second, our measurement
GLM-5.3: 86tokens/sStep 5 Preview: Not measured
SizeTotal and active parameters
GLM-5.3: 753BAll activeStep 5 Preview: 600B27B active
Developer
Z.AIStepFun
Released
17 Aug 2026Not published
Origin
ChinaNot published
Input → output
Text → textText, image, video → text
Architecture
GLM MoE with DSA sparse attentionSparse mixture-of-experts; 92 layers (88 MoE), 352 routed experts with 8 selected per token plus a shared expert; grouped-query attention with 512-token sliding windows and full attention every fourth layer; 3 multi-token-prediction layers; vision tower for image and video input

Full datasheets, every price and sourceGLM-5.3 ↗Step 5 Preview ↗

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.

GLM-5.3 59.1/100Rank 23/492 of 3 levels

2 of 3 played
Foresight: complete playing field
Level 26 ptsTurn 10 / 18

Step 5 Preview 59.9/100Rank 42/491 of 3 levels

1 of 3 played
Foresight: complete playing field
Level 122 ptsTurn 28 / 28

Points per level

LevelGLM-5.3Step 5 Preview
Level 1Second Thoughts
27 ptsSurvived
22 ptsSurvived
Level 2Pressure Pot
6 ptsOut of lives
Pending
Level 3Hide or Flight
Pending
Pending

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.

GLM-5.3 25.6/100Rank 39/50

Cleared 2 of 5
Latch: complete playing field
Level 512.2 ptsTurn 14 / 40

Step 5 Preview 40.7/100Rank 28/50

Cleared 4 of 5
Latch: complete playing field
Level 515 ptsTurn 35 / 40

Points per level

LevelGLM-5.3Step 5 Preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9 ptsCleared
9 ptsCleared
Level 3Relay vault
7.6 ptsFinished early
18.6 ptsCleared
Level 4Passing bay
3.2 ptsFinished early
15.6 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
12.2 ptsFinished early
15 ptsFinished early

Newton's Mirror

Same task instructions

Physics, perspective and recursive reflections, tested together. Explore the test ↗

The judgment

GLM-5.3

The sphere has readable rounded volume, and the compact black blob remains distinctly above it, supporting pre-impact separation. The extensive red and cyan coatings do not establish the required interaction history or paint scale. The sphere and black are substantially displaced downward. A centered upper panel, paired side patches and a vertically aligned partial floor image provide limited reflection cues, but ordered mirror-room repetitions and curved spherical imagery are largely missing.

Step 5 Preview

The main sphere, airborne black and small colored features occupy broadly appropriate positions. Most of the defining mirror system is absent, and paint interaction remains only partially supported. The small paint features do not visibly establish a separate volume-scale violation.

Score breakdown

CategoryGLM-5.3Step 5 Preview
State at 600 ms9.0/2520.0/25
Camera and placement9.0/1513.5/15
Reflections10.0/12020.0/120
Materials and scale7.0/107.0/10
Floor-damage reward0.0/100.0/10

Benchmark task

A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.

Selfie

Different task instructions

Visual construction and creative interpretation.

The judgment

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.

Step 5 Preview

A charming diagonal climber and warm palette communicate the central idea. Simple rounded construction, crowded limb counting, uncertain footholds and an unattached upper shelf limit its physical coherence. Growth bands and the yarn trail add specificity, but the requested material distinctions and unravelled bootie remain underdeveloped.

Score breakdown

CategoryGLM-5.3Step 5 Preview
Task & likeness9.0/106.0/10
Anatomy & construction7.0/104.5/10
Space & placement7.0/105.0/10
Light & reflections8.0/105.5/10
Purposeful detail8.0/105.5/10
Artistry & character7.0/105.0/10
Materials & effects7.5/106.0/10
Visual integrity8.0/105.0/10

Benchmark task

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.

Step 5 Preview

Character scenes test expression, anatomy, materials and coherent visual construction.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

GLM-5.3

Recognizable Mona Lisa motifs include the dark veil, restrained smile, folded hands and muted landscape. Clean silhouettes and balanced framing support the portrait, but the frontal symmetry, elongated face, minimally articulated hands and broad background bands make the replication basic. Facial shading offers some volume; clothing and landscape remain mostly flat.

Step 5 Preview

A recognizable, coherent simplification with purposeful facial contours and differentiated fingers. These provide more construction and detail than the broad silhouette alone suggests. The oversized face, frontal seated pose, unresolved wrists and sparse landscape still substantially limit likeness, depth and finish.

Score breakdown

CategoryGLM-5.3Step 5 Preview
Task & likeness3.0/104.0/10
Anatomy & construction2.0/104.0/10
Space & placement3.0/104.0/10
Light & reflections4.5/103.5/10
Purposeful detail3.0/104.0/10
Artistry & character2.5/104.0/10
Materials & effects3.5/103.0/10
Visual integrity4.0/103.5/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Same task instructions

Creativity, perspective and visual beauty.

The judgment

GLM-5.3

A cohesive, colorful beach illustration with an inviting sunset, readable animals and playful foreground objects. Crisp silhouettes and small accessories reward inspection. Depth remains shallow, airborne dolphins lack convincing launch splashes, and several objects lack grounding shadows. The broad dark shape across the sun weakens the focal hierarchy.

Step 5 Preview

A recognizable sunset beach with clear warm-cool contrast and playful accessories. Basic animal construction, shallow foreground placement and schematic reflections limit spatial and physical credibility. Sparse descriptive detail and abruptly ended sky bands constrain the finish.

Score breakdown

CategoryGLM-5.3Step 5 Preview
Task & likeness8.5/104.0/10
Anatomy & construction7.5/103.0/10
Space & placement7.0/103.5/10
Light & reflections7.0/103.5/10
Purposeful detail8.0/103.0/10
Artistry & character7.5/103.0/10
Materials & effects6.5/103.5/10
Visual integrity7.5/104.0/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Same task instructions

Physical reasoning, light and visual reconstruction.

The judgment

GLM-5.3

This benchmark has not been assessed yet.

Step 5 Preview

This benchmark has not been assessed yet.

Benchmark task

A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.

Raccoon

Same task instructions

Scene composition and interacting subjects.

The judgment

GLM-5.3

The raccoon rides on the dog's back, and the dog reaches toward visible handlebars. Expressive faces and clean colors make the action readable. Overlapping paws and hindquarters weaken anatomical clarity, while the vehicle resembles a flat board with a thin steering post. The wake suggests motion, but water contact, shadows and reflections receive little development.

Step 5 Preview

Recognizable animals, a bright palette and identifying accessories support a basic cartoon. Primitive anatomy, partial seated support, unresolved steering and weak hull-water contact limit the central action. Lighting and spray provide atmosphere without establishing convincing physical depth.

Score breakdown

CategoryGLM-5.3Step 5 Preview
Task & likeness6.5/104.0/10
Anatomy & construction4.5/104.5/10
Space & placement5.5/103.0/10
Light & reflections4.0/103.5/10
Purposeful detail5.0/104.0/10
Artistry & character4.0/103.5/10
Materials & effects5.0/103.0/10
Visual integrity7.5/103.0/10

Benchmark task

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.

Pelican

Same task instructions

Subject construction and spatial relationships.

The judgment

GLM-5.3

The expressive pelican, broad bill and clean coastal composition make the subject immediately readable. Both legs connect to the body and reach pedals, but the front wheel lacks a connected fork and the wings do not engage visible handlebars. Crisp spokes and feather lines add interest; flat lighting, absent ground shadows and a fish floating above the horizon weaken physical coherence.

Step 5 Preview

The pelican and bicycle are recognizable, with a pleasant palette and basic diffuse shading. The riding relationship fails physically: the bird is unsupported, the front wheel is unmounted, and pedalling is unresolved. Simple geometric construction and sparse material treatment further limit the drawing.

Score breakdown

CategoryGLM-5.3Step 5 Preview
Task & likeness7.5/103.0/10
Anatomy & construction4.0/103.0/10
Space & placement6.0/103.0/10
Light & reflections4.0/103.0/10
Purposeful detail6.5/104.0/10
Artistry & character6.5/103.0/10
Materials & effects5.0/103.0/10
Visual integrity5.5/102.0/10

Benchmark task

A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.