STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Grok 4.7 vs Hy4 preview

Grok 4.7 leads Hy4 preview by 3.3 points on StealthMark, 47.2 to 43.9. Hy4 preview leads on 7 of 9 benchmarks and Grok 4.7 on 2, including both games. Hy4 preview scores higher on Beach, with its largest category advantage in artistry & character.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

47.2/100Overall rank 28/58
43.9/100Overall rank 34/58

General Intelligence

48.4/100
41.3/100

Visual Intelligence

44.8/100
48.6/100

Reasoning efficiency

How many reasoning tokens a model needs for the quality it delivers.

Single-step reasoning How much it reasons to understand a task

Multi-step reasoning How much it keeps reasoning as a task goes on

Cost efficiency

How much Performance you get for your money.

Open or local

Open modelApache-2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Grok 4.7
  • Hy4 preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Grok 4.7 scores higher on StealthMark and runs 2.9× faster in our speed test. Hy4 preview is 2.4× cheaper per output token and takes 2× more context.

  • Grok 4.7
  • Hy4 preview
  • Other models
  • Median
PricePer 1M output tokens, input below
Grok 4.7: $6$2 inputHy4 preview: $2.502.4× cheaper$0.83 input
Context windowTokens per request, max output below
Grok 4.7: 500KHy4 preview: 1M2× larger64K max output
Output speedTokens per second, our measurement
Grok 4.7: 1852.9× fastertokens/sHy4 preview: 64tokens/s
SizeTotal and active parameters
Grok 4.7: Not disclosedHy4 preview: 770B49B active
Developer
SpaceXAITencent Hy Team
Released
21 Sep 202628 Aug 2026
Origin
United StatesChina
Input → output
Text, image → textText → text
Architecture
Not publishedMoE; 78-layer backbone with Gated DSA, 256 routed experts + 1 shared expert, top-8 routed experts active, plus native MTP layer

Full datasheets, every price and sourceGrok 4.7 ↗Hy4 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.

Grok 4.7 72.6/100Rank 4/54

Survived 3 of 3
Foresight: complete playing field
Level 316 ptsTurn 20 / 20

Hy4 preview 53.1/100Rank 17/54

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

Points per level

LevelGrok 4.7Hy4 preview
Level 1Second Thoughts
25 ptsSurvived
26 ptsSurvived
Level 2Pressure Pot
13 ptsSurvived
6 ptsOut of lives
Level 3Hide or Flight
16 ptsSurvived
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.

Grok 4.7 65.4/100Rank 23/55

Cleared 4 of 5
Latch: complete playing field
Level 520.4 ptsTurn 28 / 40

Hy4 preview 35.6/100Rank 38/55

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

Points per level

LevelGrok 4.7Hy4 preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
6 ptsFinished early
Level 3Relay vault
11.6 ptsFinished early
18 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
15.8 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.4 ptsCleared
18.2 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

Grok 4.7

Some sphere reflections are correctly placed, with useful size progression and a floor image. Their overlapping side continuations and inverted floor paint order provide additional local optical cues. The gross paint sequence is recognizable, although crimson is a little too low. Incorrect lamp projections and absent nested and receding imagery still leave the mirror system largely incomplete.

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.

Score breakdown

CategoryGrok 4.7Hy4 preview
State at 600 ms23.0/2518.0/25
Camera and placement12.5/1511.5/15
Reflections26.0/12029.5/120
Materials and scale6.5/107.5/10
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

Grok 4.7

The bold spiral dominates an appealing, restrained silhouette, with crisp angular turns and subtle charcoal highlights. However, a visible background gap separates the shell from the body, making the shell appear suspended. The connected head and delicate eye stalks read clearly, while shading and small features remain simple.

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.

Score breakdown

CategoryGrok 4.7Hy4 preview
Task & likeness7.0/106.0/10
Anatomy & construction5.0/105.5/10
Space & placement5.5/107.5/10
Light & reflections4.0/107.0/10
Purposeful detail2.5/106.5/10
Artistry & character3.5/105.0/10
Materials & effects2.5/107.0/10
Visual integrity7.5/105.5/10

Benchmark task

Grok 4.7

A dark snail with a geometric spiral shell tests silhouette, curved construction and restrained material shading.

Hy4 preview

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

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Grok 4.7

Dark clothing, overlapping hands and a restrained smile make the reference recognizable. The broad frontal face, elongated neck and oversized head weaken likeness and anatomical proportion; rounded hands lack convincing fingers. Gentle facial shading suggests volume, while clothing and landscape remain flat. Angular veil overlaps and a hard horizontal background boundary weaken the finish.

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.

Score breakdown

CategoryGrok 4.7Hy4 preview
Task & likeness2.0/102.5/10
Anatomy & construction2.0/102.5/10
Space & placement3.0/102.5/10
Light & reflections1.5/101.5/10
Purposeful detail3.0/102.5/10
Artistry & character2.5/101.5/10
Materials & effects2.0/102.5/10
Visual integrity3.0/104.0/10

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

Grok 4.7

The warm sunset, blue water and scattered beach activities create a cheerful, readable composition. Animals and equipment use basic silhouettes, with limited anatomical detail and grounding. The sun reflection forms a rigid tapered strip, and foreground objects lack cast shadows. Clean shapes support the illustration, but depth, materials and drawing complexity remain modest.

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.

Score breakdown

CategoryGrok 4.7Hy4 preview
Task & likeness7.5/108.5/10
Anatomy & construction4.5/105.5/10
Space & placement5.5/106.5/10
Light & reflections6.0/105.0/10
Purposeful detail5.0/106.0/10
Artistry & character3.5/105.5/10
Materials & effects4.5/105.0/10
Visual integrity6.0/106.0/10

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

Grok 4.7

This benchmark has not been assessed yet.

Hy4 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

Grok 4.7

The raccoon rides clearly on the dog's back, and expressive faces, bright colors and a readable orange hull create a playful composition. Steering is unresolved: the dog's visible paws rest on the deck rather than grasping the controls. Simple body shapes and ribbonlike wake limit construction and movement. The glowing sun produces little corresponding illumination or reflection.

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.

Score breakdown

CategoryGrok 4.7Hy4 preview
Task & likeness7.0/107.0/10
Anatomy & construction4.5/104.0/10
Space & placement6.5/106.0/10
Light & reflections4.5/106.5/10
Purposeful detail5.5/105.5/10
Artistry & character5.5/104.5/10
Materials & effects5.5/105.5/10
Visual integrity3.5/105.0/10

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

Grok 4.7

The pelican reads clearly through its long bill, throat pouch and curved neck. Clean pastel shapes and balanced scenery make an appealing illustration. The riding mechanism is less convincing: feet lack clear pedal contact, steering is unresolved, and the frame lacks a coherent drivetrain. Simple shading and sparse feather detail limit depth and finish.

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.

Score breakdown

CategoryGrok 4.7Hy4 preview
Task & likeness7.5/107.5/10
Anatomy & construction4.5/104.5/10
Space & placement6.5/106.5/10
Light & reflections6.0/107.0/10
Purposeful detail6.0/106.0/10
Artistry & character5.5/105.0/10
Materials & effects5.5/105.0/10
Visual integrity6.0/107.0/10

Benchmark task

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