STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Hy4 preview vs Muse Wonder

Muse Wonder leads Hy4 preview by 13.1 points on StealthMark, 57.0 to 43.9. It leads on 7 of 9 benchmarks, including Latch, and Hy4 preview on 2, including Foresight. Muse Wonder scores higher on Ground Truth.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

43.9/100Overall rank 30/53
57.0/100Overall rank 10/53

General Intelligence

41.3/100
53.1/100

Visual Intelligence

48.6/100
64.0/100

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

  • Hy4 preview

Open or local

Open modelApache-2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Hy4 preview
  • Muse Wonder
  • Other models
  • Median

DATASHEET

Specs and pricing

Hy4 preview is 8× cheaper per output token. Muse Wonder scores higher on StealthMark and runs 8.9× faster in our speed test. Both take about 1M tokens of context.

  • Hy4 preview
  • Muse Wonder
  • Other models
  • Median
PricePer 1M output tokens, input below
Hy4 preview: $2.508× cheaper$0.83 inputMuse Wonder: $20$4 input
Context windowTokens per request, max output below
Hy4 preview: 1MTied64K max outputMuse Wonder: 1MTied
Output speedTokens per second, our measurement
Hy4 preview: 64tokens/sMuse Wonder: 5708.9× fastertokens/s
SizeTotal and active parameters
Hy4 preview: 770B49B activeMuse Wonder: Not disclosed
Developer
Tencent Hy TeamMeta
Released
28 Aug 202612 Oct 2026
Origin
ChinaUnited States
Input → output
Text → textText, image, video, audio, PDF → text
Architecture
MoE; 78-layer backbone with Gated DSA, 256 routed experts + 1 shared expert, top-8 routed experts active, plus native MTP layerNot published

Full datasheets, every price and sourceHy4 preview ↗Muse Wonder ↗

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.

Hy4 preview 53.1/100Rank 14/47

Survived 1 of 3
Foresight: complete playing field
Level 311 ptsTurn 16 / 20

Muse Wonder 52.3/100Rank 17/47

Survived 0 of 3
Foresight: complete playing field
Level 311 ptsTurn 17 / 20

Points per level

LevelHy4 previewMuse Wonder
Level 1Second Thoughts
26 ptsSurvived
16 ptsOut of lives
Level 2Pressure Pot
6 ptsOut of lives
10 ptsOut of lives
Level 3Hide or Flight
11 ptsOut of lives
11 ptsOut of lives

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.

Hy4 preview 35.6/100Rank 31/48

Cleared 3 of 5
Latch: complete playing field
Level 518.2 ptsTurn 19 / 40

Muse Wonder 67.0/100Rank 17/48

Cleared 5 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

Points per level

LevelHy4 previewMuse Wonder
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
6 ptsFinished early
9 ptsCleared
Level 3Relay vault
18 ptsCleared
18.8 ptsCleared
Level 4Passing bay
15.8 ptsClearedFinished early · 3 beacons left
17.8 ptsClearedFinished early · 1 beacon left
Level 5Second thoughts
18.2 ptsFinished early
20.6 ptsCleared

Newton's Mirror

Same task instructions

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

The judgment

Hy4 preview

The central sphere, compact airborne black bead and broad paint ordering are supported. Contact and transport history remain partly unresolved. The optical system provides only isolated first images and light patches, with little evidence of the extensive ordered reflection structure. Rounded metal and paint gloss are more successful than the reflected contents.

Muse Wonder

The flattened cyan cap, separate airborne black blob and crimson droplets support much of the contact sequence, although crimson adhesion and forward carriage remain unresolved. Main-sphere placement is broadly compatible with the prescribed view. Sparse isolated mirror images replace the defining repeated room structure and curved nested reflections. The crimson mass is visibly oversized, and the top-center lamp image is missing.

Score breakdown

CategoryHy4 previewMuse Wonder
State at 600 ms18.0/2522.0/25
Camera and placement11.5/1512.0/15
Reflections29.5/12021.5/120
Materials and scale7.5/107.5/10
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

Hy4 preview

A cohesive, appealing illustration with a serene face, luminous palette and complete framing. The separated head and torso weaken anatomical coherence, while crowded wing attachments and angular sash folds limit the requested suppleness. Clean execution and decorative detail exceed the clarity of the underlying construction.

Muse Wonder

An appealing, coherent cartoon with a readable effortful expression and clear forefeet gripping the trunk. Soft colours and controlled contours support its tenderness. Smooth ears, stiff foreleg construction, limited surface texture and uncertain seed contact keep the execution below intricate illustration quality.

Score breakdown

CategoryHy4 previewMuse Wonder
Task & likeness6.0/107.5/10
Anatomy & construction5.5/107.0/10
Space & placement7.5/107.5/10
Light & reflections7.0/107.0/10
Purposeful detail6.5/107.5/10
Artistry & character5.0/106.5/10
Materials & effects7.0/106.5/10
Visual integrity5.5/108.0/10

Benchmark task

Hy4 preview

A young blue dragon floating among clouds tests curved anatomy, expressive features and the contrast between soft clouds and glossy surfaces.

Muse Wonder

A small elephant protecting a delicate seed tests expressive anatomy, physical contact and contrasting organic materials.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Hy4 preview

A recognizable but basic Mona Lisa interpretation with a cohesive earthy palette and atmospheric hills. The rigid neck, generic face and unresolved folded-hand pose limit replication and anatomy. Large silhouettes and layer boundaries are comparatively clear, warranting stronger integrity credit than the sparse detail and simplified construction.

Muse Wonder

A competent illustrative interpretation with controlled curves, readable details and coherent depth layers. Facial, hair and garment shading demonstrate more development than basic construction. Replication remains limited by the frontal pose, elongated face and pronounced smile; crowded fingers, weak contact shadows and smooth materials constrain anatomical and painterly conviction.

Score breakdown

CategoryHy4 previewMuse Wonder
Task & likeness2.5/105.5/10
Anatomy & construction2.5/105.5/10
Space & placement2.5/105.5/10
Light & reflections1.5/105.5/10
Purposeful detail2.5/105.5/10
Artistry & character1.5/105.5/10
Materials & effects2.5/105.0/10
Visual integrity4.0/106.5/10

Benchmark task

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

Beach

Different task instructions

Creativity, perspective and visual beauty.

The judgment

Hy4 preview

A cheerful beach illustration fulfills the visible subject requirements with coherent foreground construction and a harmonious sunset palette. Shallow depth, schematic reflections, ambiguous blue airborne forms and exposed geometry beneath the sunset limit its finish. Small accessories are readable, but materials and surface detail remain simplified.

Muse Wonder

A lively beach illustration with expressive animals, controlled colour transitions and unusually readable accessories. Connected graphic forms make the activities recognizable. Crowded overlaps, compressed depth, schematic joints, weak directional shadows and limited material variation constrain its physical coherence and refinement.

Score breakdown

CategoryHy4 previewMuse Wonder
Task & likeness8.5/108.5/10
Anatomy & construction5.5/106.0/10
Space & placement6.5/106.5/10
Light & reflections5.0/106.5/10
Purposeful detail6.0/109.0/10
Artistry & character5.5/107.0/10
Materials & effects5.0/106.0/10
Visual integrity6.0/107.0/10

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

Hy4 preview

This benchmark has not been assessed yet.

Muse Wonder

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

Different task instructions

Scene composition and interacting subjects.

The judgment

Hy4 preview

A lively cartoon communicates the animal pair traveling across water. Curving waves, rising spray and locally modeled gray forms strengthen motion and volume. Ambiguous seating, simplified joints and unclear control routing limit construction. Competing focal elements, decorative foam and inconsistent illumination leave the finish uneven.

Muse Wonder

An expressive, coherent cartoon demonstrates the requested riding and steering interaction. Clean contours, differentiated accessories and energetic spray support its appeal. Concealed seated contacts, compressed vehicle perspective and weak directional lighting limit physical resolution despite the detailed presentation.

Score breakdown

CategoryHy4 previewMuse Wonder
Task & likeness7.0/107.5/10
Anatomy & construction4.0/105.5/10
Space & placement6.0/106.5/10
Light & reflections6.5/104.5/10
Purposeful detail5.5/107.5/10
Artistry & character4.5/105.5/10
Materials & effects5.5/107.0/10
Visual integrity5.0/107.0/10

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

Different task instructions

Subject construction and spatial relationships.

The judgment

Hy4 preview

A recognizable, playful pelican cyclist with readable wheels, accessories and landscape layers. Form shading and ground shadows provide competent depth. Angular legs, uncertain pedal engagement and absent steering contact limit the riding construction; crowded overlaps and simple surfaces constrain refinement.

Muse Wonder

A controlled, expressive seaside illustration with a distinctive pelican, coherent bicycle geometry and successfully resolved graphic detail. Visible pedal support and plausible occlusion strengthen the riding construction. Aligned wheels and layered scenery establish placement. Limited cast shadows, simplified leg articulation and restrained material modeling constrain its physical finish.

Score breakdown

CategoryHy4 previewMuse Wonder
Task & likeness7.5/108.5/10
Anatomy & construction4.5/106.0/10
Space & placement6.5/107.5/10
Light & reflections7.0/105.5/10
Purposeful detail6.0/108.5/10
Artistry & character5.0/107.5/10
Materials & effects5.0/106.0/10
Visual integrity7.0/108.0/10

Benchmark task

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