stealthmodels.

MODEL FIELD GUIDE

Hy4 Preview: Newton's Mirror

Apache-2.0 MoE preview with 770B total parameters, 49B active and a million-token context. Sparse attention and multi-token prediction support long-input workloads.

Drawn by this model01 / 01
Newton's Mirror benchmark result generated by this model
SVG BENCHMARKNewton's MirrorView result

A good fit for

Long-document analysis and research on large GPU systems, with the freedom to inspect and adapt the weights.

Context window
1,000,000tokens[1]
Active parameters
49Bparameters[1]
License
Apache-2.0[1]
Model factsArchitecture, context & capabilities
Developer
Tencent Hy Team[1]
Origin
China[2]
Family
Hy4[1]
Context window
1,000,000 tokens[1]
Architecture
MoE; 78-layer backbone with Gated DSA, 256 routed experts + 1 shared expert, top-8 routed experts active, plus native MTP layer[1]
Total parameters
770B[1]
Active parameters per token
49B[1]
Input
text[1]
Output
text[1]
API access & pricingProviders, model IDs & rates
Run it locallyWeights, memory & deployment

rack-scale

[1] [3]
  • Official Hy4-preview-FP8 repository814 GB storage · FP8[3]
Measurements & sources3 primary references

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.