stealthmodels.

MODEL FIELD GUIDE

GLM-5.3: Pelican

Large open-weight reasoning model combining sparse attention with a million-token context. The weights use Z.ai's custom GLM-5.3 license.

Drawn by this model01 / 01
Pelican benchmark result generated by this model
SVG BENCHMARKPelicanView result

A good fit for

Text reasoning and coding agents that need long context and deployment control on substantial GPU infrastructure.

Context window
1,000,000tokens[3]
Total parameters
753Bparameters[1]
License
GLM-5.3 License[2]
Model factsArchitecture, context & capabilities
Developer
Z.AI[1] [2]
Family
GLM-5[1] [2]
Context window
1,000,000 tokens[3]
Architecture
GLM MoE with DSA sparse attention[1]
Total parameters
753B[1]
Input
text[1]
Output
text[1]
API access & pricingOpenRouter · $0.07 input / $7 output · per 1M tokens

Vercel AI Gateway / provider routes; input 0.7 USD/1M; cached read 0.12/1M; output 2.2/1M; Vercel gateway shows multiple provider routes; displayed minimum/current route pricing is not universal Z.AI direct pricing.

[3]
  • OpenRouterObserved 2026-10-06
    Input $0.07Output $7Cached read $0.065

    per 1M tokens

    z-ai/glm-5.3[5]
  • Vercel AI Gateway / provider routesObserved 2026-10-06
    Input $0.7Output $2.2Cached read $0.12

    per 1M tokens

    Available

    zai/glm-5.3[3]
Run it locallyWeights, memory & deployment

rack-scale

[1] [4] [6]
  • Unsloth UD-Q4_K_XL GGUF467 GB storage · ~4-bit[4]
Measurements & sources6 primary references · Speed & serving conditions
  • Vercel AI GatewayObserved 2026-10-06

    412 tokens/s decode

    200 ms to first token

    [3]
  • Artificial AnalysisObserved 2026-10-06

    73.3 tokens/s decode

    max

    [6]

StealthMark score

StealthMark measures fluid and visual intelligence of AI models.

General and Visual

General Intelligence

Perspective, anatomy, correct shadows, purposeful detail and physical consistency.

Visual Intelligence

Likeness, anatomy, detail, light, materials, composition and artistic expression.

Judging

Frontier Models blindly judge the AI generation unbiased through an intricate process. Our researchers control for mistakes.

Overall score

Overall combines weighted task scores on a scale from 0 to 100. Repeating a task does not increase its weight. Estimated means the total includes an estimate for one missing scene.

Benchmaxxing

Benchmaxx flags models that score unusually well on the familiar Pelican task compared with their other benchmark results. The percentage measures that imbalance, not the probability of training contamination. Flagged Pelican scores are excluded from Overall. Pelican never counts toward General or Visual.

We keep some prompts private to discourage test-specific optimization.

Scoring categories

Prompt & likeness

Subjects, actions and likeness.

Anatomy & construction

Coherent bodies, joints and machinery.

Space & placement

Perspective, scale and contact.

Light & reflections

Lighting, shadows and reflections.

Purposeful detail

Clear, purposeful small features.

Artistry & character

Composition, expression and drawing skill.

Materials & effects

Surfaces, texture and movement.

Visual integrity

Clean shapes, layers and edges.

BENCHMARK RESULTS

Compare results

This link opens the same results in the same order.

StealthMark benchmark results

Reset benchmark preferences?

Return to the default view, clear comparison selections and restore the advertisement.