STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6.1 Sol vs Hy4 preview

GPT-6.1 Sol leads Hy4 preview by 23.9 points on StealthMark, 67.8 to 43.9. It leads on all 9 benchmarks. GPT-6.1 Sol scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

67.8/100Overall rank 5/58
43.9/100Overall rank 34/58

General Intelligence

64.4/100
41.3/100

Visual Intelligence

74.1/100
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

  • GPT-6.1 Sol

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-6.1 Sol
  • Hy4 preview
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-6.1 Sol scores higher on StealthMark. Hy4 preview is 4× cheaper per output token and runs 25% faster in our speed test. Both take about 1.05M tokens of context.

  • GPT-6.1 Sol
  • Hy4 preview
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6.1 Sol: $10$2 inputHy4 preview: $2.504× cheaper$0.83 input
Context windowTokens per request, max output below
GPT-6.1 Sol: 1.05MTied128K max outputHy4 preview: 1MTied64K max output
Output speedTokens per second, our measurement
GPT-6.1 Sol: 51tokens/sHy4 preview: 6425% fastertokens/s
SizeTotal and active parameters
GPT-6.1 Sol: Not disclosedHy4 preview: 770B49B active
Developer
OpenAITencent Hy Team
Released
29 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 sourceGPT-6.1 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-6.1 Sol 62.0/100Rank 10/54

Survived 2 of 3
Foresight: complete playing field
Level 318 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

LevelGPT-6.1 SolHy4 preview
Level 1Second Thoughts
26 ptsSurvived
26 ptsSurvived
Level 2Pressure Pot
6 ptsOut of lives
6 ptsOut of lives
Level 3Hide or Flight
18 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.

GPT-6.1 Sol 87.6/100Rank 2/55

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-6.1 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
19.2 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-6.1 Sol

Recognizable first sphere images and several central planar lights provide limited geometric agreement. Missing outer chains, truncated panel sequences and simplified interiors across the main, side and floor spheres leave most of the recursive reflection structure unsupported.

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-6.1 SolHy4 preview
State at 600 ms24.0/2518.0/25
Camera and placement15.0/1511.5/15
Reflections35.0/12029.5/120
Materials and scale10.0/107.5/10
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-6.1 Sol

Six outward-facing heads and evenly arranged loops make the pale interlocking knot immediately readable. Uniform widths, angular inner bends and fine scales preserve its ornamental geometry. The bodies feel more like textured tubes than living muscle: shading is subdued, crossing contact shadows are weak, and visible curved seams interrupt surface continuity. Small heads have readable eyes and jaws but limited anatomical depth.

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-6.1 SolHy4 preview
Task & likeness8.5/106.0/10
Anatomy & construction7.5/105.5/10
Space & placement8.0/107.5/10
Light & reflections7.0/107.0/10
Purposeful detail7.5/106.5/10
Artistry & character7.5/105.0/10
Materials & effects7.0/107.0/10
Visual integrity8.0/105.5/10

Benchmark task

GPT-6.1 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-6.1 Sol

The recognizable pose, dark clothing and misty landscape form a coherent portrait. Soft facial shading creates volume, but the broad face, outlined eyes and simplified smile limit likeness. Overlapping hands have flattened fingers and ambiguous separation. Angular landscape shapes and sparse fabric detail keep the execution competent rather than masterful.

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-6.1 SolHy4 preview
Task & likeness6.5/102.5/10
Anatomy & construction5.5/102.5/10
Space & placement6.5/102.5/10
Light & reflections6.5/101.5/10
Purposeful detail5.5/102.5/10
Artistry & character6.5/101.5/10
Materials & effects6.0/102.5/10
Visual integrity7.0/104.0/10

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

GPT-6.1 Sol

A cohesive sunset palette, sweeping shoreline and framing palm create an appealing beach illustration. Animals, birds, play and a prominent sun reflection fulfill the brief. Connected but schematic figures and simplified dolphin anatomy limit construction; stepped reflections and mostly flat surfaces limit lighting and material depth. Small beach accessories remain readable and edges are clean.

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-6.1 SolHy4 preview
Task & likeness8.5/108.5/10
Anatomy & construction7.5/105.5/10
Space & placement7.5/106.5/10
Light & reflections7.5/105.0/10
Purposeful detail7.5/106.0/10
Artistry & character7.0/105.5/10
Materials & effects7.0/105.0/10
Visual integrity8.5/106.0/10

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-6.1 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-6.1 Sol

The masked raccoon rides the dog's back, and the dog's forepaw meets a handlebar connected to the deck. Expressive faces, a striped tail and sweeping wake create an appealing composition. Overlapping bodies compress the seating and rear-leg anatomy; hull depth and sunset illumination remain schematic.

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-6.1 SolHy4 preview
Task & likeness8.5/107.0/10
Anatomy & construction7.5/104.0/10
Space & placement7.5/106.0/10
Light & reflections6.5/106.5/10
Purposeful detail8.0/105.5/10
Artistry & character8.0/104.5/10
Materials & effects7.5/105.5/10
Visual integrity8.5/105.0/10

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

GPT-6.1 Sol

A clearly recognizable pelican rides a well-composed bicycle through a warm coastal scene. The expressive bill, restrained palette and carefully drawn wheels give the illustration character. Leg-to-pedal connections are less convincing, especially the obscured far foot. Lighting provides gentle volume but little directional shadow. The small subtitle is clipped at the lower border.

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-6.1 SolHy4 preview
Task & likeness9.0/107.5/10
Anatomy & construction7.0/104.5/10
Space & placement8.0/106.5/10
Light & reflections7.0/107.0/10
Purposeful detail8.0/106.0/10
Artistry & character8.5/105.0/10
Materials & effects7.5/105.0/10
Visual integrity8.0/107.0/10

Benchmark task

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