STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-5.6 Sol vs Hy4 preview

GPT-5.6 Sol leads Hy4 preview by 9.8 points on StealthMark, 53.7 to 43.9. It leads on 8 of 9 benchmarks, including both games, and Hy4 preview on 1. Hy4 preview scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

53.7/100Overall rank 15/58
43.9/100Overall rank 34/58

General Intelligence

51.7/100
41.3/100

Visual Intelligence

57.4/100
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

  • GPT-5.6 Sol
  • Hy4 preview
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-5.6 Sol scores higher on StealthMark and runs 27% faster in our speed test. Hy4 preview is 8× cheaper per output token. Both take about 1.05M tokens of context.

  • GPT-5.6 Sol
  • Hy4 preview
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-5.6 Sol: $20$4 inputHy4 preview: $2.508× cheaper$0.83 input
Context windowTokens per request, max output below
GPT-5.6 Sol: 1.05MTied128K max outputHy4 preview: 1MTied64K max output
Output speedTokens per second, our measurement
GPT-5.6 Sol: 8127% fastertokens/sHy4 preview: 64tokens/s
SizeTotal and active parameters
GPT-5.6 Sol: Not disclosedHy4 preview: 770B49B active
Developer
OpenAITencent Hy Team
Released
9 Jul 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 sourceGPT-5.6 Sol ↗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.

GPT-5.6 Sol 62.9/100Rank 9/54

Survived 1 of 3
Foresight: complete playing field
Level 311 ptsTurn 17 / 20

Hy4 preview 53.1/100Rank 17/54

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

Points per level

LevelGPT-5.6 SolHy4 preview
Level 1Second Thoughts
27 ptsSurvived
26 ptsSurvived
Level 2Pressure Pot
10 ptsOut of lives
6 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.

GPT-5.6 Sol 83.6/100Rank 6/55

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

LevelGPT-5.6 SolHy4 preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
10.2 ptsClearedFinished early · 1 beacon left
6 ptsFinished early
Level 3Relay vault
18.8 ptsCleared
18 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
15.8 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
18.2 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

GPT-5.6 Sol

The central sphere and paint ordering are supported, but a frontal, centrally converging chamber replaces the required corner perspective. The first wall and floor images have incorrect placement and scale relationships. Sparse reflection cues remain, while continuous outer chains, open lateral sightlines, dense planar light sequences and curved nested spherical imagery are largely missing.

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

CategoryGPT-5.6 SolHy4 preview
State at 600 ms23.0/2518.0/25
Camera and placement6.0/1511.5/15
Reflections11.0/12029.5/120
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

GPT-5.6 Sol

Six evenly spaced lobes, outward-facing heads and a clear central hexagon establish the requested knot. The ivory silhouette is controlled, but broad crossing bands resemble rigid strips, shading provides limited muscular volume, and repetitive scale lines extend across black loop openings. Small oval heads have readable eyes and mouths but limited anatomical character or moist surface detail.

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

CategoryGPT-5.6 SolHy4 preview
Task & likeness7.5/106.0/10
Anatomy & construction6.0/105.5/10
Space & placement7.0/107.5/10
Light & reflections5.0/107.0/10
Purposeful detail6.0/106.5/10
Artistry & character6.5/105.0/10
Materials & effects4.5/107.0/10
Visual integrity6.0/105.5/10

Benchmark task

GPT-5.6 Sol

A pale serpent woven into an interlocking knot tests connected anatomy, repeated structure and readable overlaps. Organic surface detail must work with the overall geometry.

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

GPT-5.6 Sol

The crossed hands, dark dress and winding landscape establish the Mona Lisa composition. Replication is limited by enlarged eyes, an elongated face and a more frontal pose. Broad gradients suggest volume, but outlined features and flattened, overlapping fingers weaken the portrait. The frame and restrained palette unify the image; visible grain adds texture without convincing painterly transitions.

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

CategoryGPT-5.6 SolHy4 preview
Task & likeness4.5/102.5/10
Anatomy & construction4.0/102.5/10
Space & placement5.5/102.5/10
Light & reflections5.0/101.5/10
Purposeful detail5.0/102.5/10
Artistry & character4.5/101.5/10
Materials & effects5.5/102.5/10
Visual integrity6.5/104.0/10

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

GPT-5.6 Sol

Clear subject coverage, developed beach details and coordinated atmospheric effects support a coherent illustration. The large dolphin floats in the sky above the horizon with no water contact or splash, and the kite line ends at the flyer's upper arm without a clear grip. Schematic tube-limbed anatomy and the turtle's overhead viewpoint against the low horizon are further limits.

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

CategoryGPT-5.6 SolHy4 preview
Task & likeness8.5/108.5/10
Anatomy & construction5.0/105.5/10
Space & placement5.5/106.5/10
Light & reflections7.0/105.0/10
Purposeful detail7.0/106.0/10
Artistry & character6.0/105.5/10
Materials & effects7.0/105.0/10
Visual integrity5.0/106.0/10

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

GPT-5.6 Sol

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

GPT-5.6 Sol

Expressive faces, bold silhouettes and layered waves make an appealing cartoon. The raccoon sits convincingly behind the dog's shoulders, and the dog's forward paw reaches the steering grip. Steering construction and seated support remain somewhat ambiguous. The glowing sunset lacks a corresponding warm reflection or consistent illumination on the riders.

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

CategoryGPT-5.6 SolHy4 preview
Task & likeness6.5/107.0/10
Anatomy & construction5.0/104.0/10
Space & placement6.5/106.0/10
Light & reflections6.5/106.5/10
Purposeful detail7.5/105.5/10
Artistry & character5.0/104.5/10
Materials & effects7.0/105.5/10
Visual integrity5.0/105.0/10

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

GPT-5.6 Sol

The expressive pelican and balanced coastal composition remain appealing, but a sky-colored slit between the neck contours above the wing leaves the central anatomy incoherent. This visible construction and layering defect prevents a clean-integrity assessment. Clustered feet lack clear pedal contacts and the chain routing is schematic; lighting and water reflections remain graphic.

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

CategoryGPT-5.6 SolHy4 preview
Task & likeness8.5/107.5/10
Anatomy & construction5.0/104.5/10
Space & placement7.5/106.5/10
Light & reflections7.5/107.0/10
Purposeful detail8.0/106.0/10
Artistry & character6.5/105.0/10
Materials & effects7.0/105.0/10
Visual integrity4.5/107.0/10

Benchmark task

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