STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-5.6 Sol vs Inkling-Small

GPT-5.6 Sol leads Inkling-Small by 26.5 points on StealthMark, 54.1 to 27.6. It leads on all 9 benchmarks. GPT-5.6 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

54.1/100Overall rank 12/53
27.6/100Overall rank 43/53

General Intelligence

51.9/100
25.5/100

Visual Intelligence

58.2/100
31.1/100

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

  • Inkling-Small

Open or local

Open modelApache 2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-5.6 Sol
  • Inkling-Small
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1.05M tokens of context.

  • GPT-5.6 Sol
  • Inkling-Small
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-5.6 Sol: $20$4 inputInkling-Small: No list price
Context windowTokens per request, max output below
GPT-5.6 Sol: 1.05MTied128K max outputInkling-Small: 1MTied
Output speedTokens per second, our measurement
GPT-5.6 Sol: 81tokens/sInkling-Small: Not measured
SizeTotal and active parameters
GPT-5.6 Sol: Not disclosedInkling-Small: 276B12B active
Developer
OpenAIThinking Machines Lab
Released
9 Jul 2026Not published
Origin
United StatesNot published
Input → output
Text, image → textText, image, audio → text
Architecture
Not published42-layer decoder-only transformer with sparse mixture-of-experts feed-forward (6 of 256 routed experts plus 2 shared per token); hybrid local and global attention; natively multimodal with a hierarchical patch image encoder and discrete-token audio

Full datasheets, every price and sourceGPT-5.6 Sol ↗Inkling-Small ↗

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 8/49

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

Inkling-Small 30.2/100Rank 29/49

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 17 / 20

Points per level

LevelGPT-5.6 SolInkling-Small
Level 1Second Thoughts
27 ptsSurvived
9 ptsOut of lives
Level 2Pressure Pot
10 ptsOut of lives
6 ptsOut of lives
Level 3Hide or Flight
11 ptsOut of lives
8 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 5/50

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

Inkling-Small 34.7/100Rank 34/50

Cleared 3 of 5
Latch: complete playing field
Level 518 ptsTurn 40 / 40

Points per level

LevelGPT-5.6 SolInkling-Small
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
10.2 ptsClearedFinished early · 1 beacon left
9.8 ptsCleared
Level 3Relay vault
18.8 ptsCleared
2.8 ptsFinished early
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
8 ptsFinished early
Level 5Second thoughts
20.6 ptsCleared
18 ptsCleared

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.

Inkling-Small

The sphere's apparent floor support, separate dark feature and broad paint ordering justify partial state credit. The major weakness is the largely missing mirror system: isolated side images and faint floor echoes do not establish repeated virtual rooms or curved spherical mapping. Downward framing, the oversized frontal panel, unresolved paint transport and satin surface appearance remain distinct limitations.

Score breakdown

CategoryGPT-5.6 SolInkling-Small
State at 600 ms23.0/2514.0/25
Camera and placement6.0/153.0/15
Reflections11.0/1208.0/120
Materials and scale7.5/102.5/10
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.

Inkling-Small

The faces and dripping caps communicate a cute mushroom scene, but simple construction and weak spatial relationships limit the result. The defining foot-stamping action is unresolved, the flattering portrait is smaller than its painter, and the requested material contrasts are only partly conveyed.

Score breakdown

CategoryGPT-5.6 SolInkling-Small
Task & likeness7.5/102.5/10
Anatomy & construction6.0/101.5/10
Space & placement7.0/103.5/10
Light & reflections5.0/103.0/10
Purposeful detail6.0/104.5/10
Artistry & character6.5/103.0/10
Materials & effects4.5/103.5/10
Visual integrity6.0/102.0/10

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.

Inkling-Small

Character scenes test expression, anatomy, materials and coherent visual construction.

Mona Lisa

Same 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.

Inkling-Small

A recognizable but rudimentary Mona Lisa interpretation. Facial shading and subdued colors provide coherence, while the frontal blocklike torso, unresolved wrists, fingerless hands and shallow landscape substantially limit likeness, construction and finish.

Score breakdown

CategoryGPT-5.6 SolInkling-Small
Task & likeness4.5/102.5/10
Anatomy & construction4.0/102.5/10
Space & placement5.5/103.0/10
Light & reflections5.0/102.5/10
Purposeful detail5.0/102.0/10
Artistry & character4.5/102.5/10
Materials & effects5.5/102.0/10
Visual integrity6.5/103.0/10

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

The purple-to-gold sunset, framing palms and varied beach activities create an appealing, coherent illustration. The sun’s reflection establishes a clear focal path. Figures and animals are recognizable but geometrically simplified; airborne dolphins lack convincing splashes, and the boat reflection is schematic. Clean silhouettes and playful details succeed more strongly than anatomical depth or material realism.

Inkling-Small

A recognizable sunset beach with a clear focal sun and appealing color transitions. Connected fish silhouettes and layered scenery establish basic coherence. Primitive figures, ambiguous recreation, sparse descriptive detail and weak grounding limit construction and depth. The aligned reflection supplies a useful lighting cue, but shadows and material effects remain underdeveloped.

Score breakdown

CategoryGPT-5.6 SolInkling-Small
Task & likeness8.5/103.5/10
Anatomy & construction6.0/103.0/10
Space & placement7.0/103.0/10
Light & reflections6.5/103.0/10
Purposeful detail7.0/103.0/10
Artistry & character6.5/103.0/10
Materials & effects6.5/102.5/10
Visual integrity7.0/102.0/10

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.

Inkling-Small

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.

Inkling-Small

Recognizable animals, readable accessories and an appealing sunset support a coherent basic cartoon. Rounded construction leaves joints, riding support and steering unresolved. Decorative gradients contribute atmosphere, but directional lighting, distinct materials and convincing water displacement are weakly demonstrated.

Score breakdown

CategoryGPT-5.6 SolInkling-Small
Task & likeness6.5/104.0/10
Anatomy & construction5.0/103.0/10
Space & placement6.5/104.0/10
Light & reflections6.5/105.0/10
Purposeful detail7.5/105.5/10
Artistry & character5.0/104.0/10
Materials & effects7.0/105.0/10
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.

Inkling-Small

The pelican is immediately recognizable, and its sweeping neck, shaped bill and orderly spokes provide character. Riding remains only partially realized: legs, pedal engagement, steering and seat support cannot be read confidently. Controlled graphic effects add atmosphere, but simplified construction and weak grounding keep the result basic.

Score breakdown

CategoryGPT-5.6 SolInkling-Small
Task & likeness8.5/104.0/10
Anatomy & construction5.0/103.0/10
Space & placement7.5/103.0/10
Light & reflections7.5/103.0/10
Purposeful detail8.0/104.5/10
Artistry & character6.5/105.0/10
Materials & effects7.0/104.5/10
Visual integrity4.5/103.0/10

Benchmark task

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