STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-5.6 Terra vs Inkling-Small

GPT-5.6 Terra leads Inkling-Small by 18.2 points on StealthMark, 45.8 to 27.6. It leads on 8 of 9 benchmarks, including Latch, and Inkling-Small on 1, including Foresight. GPT-5.6 Terra 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

45.8/100Overall rank 25/53
27.6/100Overall rank 43/53

General Intelligence

41.9/100
25.5/100

Visual Intelligence

52.7/100
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

  • GPT-5.6 Terra
  • Inkling-Small

Open or local

Open modelApache 2.0

BENCHMARK BY BENCHMARK

Where each model leads

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

DATASHEET

Specs and pricing

Both take about 1.05M tokens of context.

  • GPT-5.6 Terra
  • Inkling-Small
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-5.6 Terra: $12$2 inputInkling-Small: No list price
Context windowTokens per request, max output below
GPT-5.6 Terra: 1.05MTied128K max outputInkling-Small: 1MTied
Output speedTokens per second, our measurement
GPT-5.6 Terra: 102tokens/sInkling-Small: Not measured
SizeTotal and active parameters
GPT-5.6 Terra: 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 Terra ↗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 Terra 30.1/100Rank 31/49

Survived 0 of 3
Foresight: complete playing field
Level 36 ptsTurn 7 / 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 TerraInkling-Small
Level 1Second Thoughts
5 ptsOut of lives
9 ptsOut of lives
Level 2Pressure Pot
9 ptsOut of lives
6 ptsOut of lives
Level 3Hide or Flight
6 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 Terra 80.0/100Rank 10/50

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 TerraInkling-Small
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
9.8 ptsCleared
Level 3Relay vault
19.2 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 Terra

The real sphere and airborne black blob are substantially too low in the complete frame after accounting for aspect ratio. The first wall and floor reflections have incompatible placement, relative size or silhouette. Both lateral regions lack the references' receding lane-and-chain organization. The few recognizable mirror images provide limited optical structure. The main, side and floor spheres replace nested mirror imagery with smooth bands, while sparse planar light patches and broad spherical highlights fail to establish coherent repeated emitter mapping.

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 TerraInkling-Small
State at 600 ms24.0/2514.0/25
Camera and placement6.0/153.0/15
Reflections7.0/1208.0/120
Materials and scale5.5/102.5/10
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 Terra

Six ivory heads and rounded lobes create a striking radial emblem around a clear hexagonal opening. Soft shading gives the bodies volume, but abrupt rectangular and diagonal band endings make the continuous alternating weave ambiguous. Repetitive scale lines and simplified faces convey an ornamental serpent more convincingly than living anatomy.

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 TerraInkling-Small
Task & likeness7.5/102.5/10
Anatomy & construction5.5/101.5/10
Space & placement7.0/103.5/10
Light & reflections7.5/103.0/10
Purposeful detail6.5/104.5/10
Artistry & character5.5/103.0/10
Materials & effects6.5/103.5/10
Visual integrity5.0/102.0/10

Benchmark task

GPT-5.6 Terra

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 Terra

The dark clothing, central portrait and restrained smile evoke the Mona Lisa, but replication is limited by the broad face, elongated neck, nearly frontal pose and indistinct landscape. Soft gradients give the face some volume. Crossed arms become rounded masses without readable fingers or wrists, and the expression lacks the original's subtlety. Clean framing and curves support an otherwise basic, uneven portrait.

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 TerraInkling-Small
Task & likeness4.0/102.5/10
Anatomy & construction3.0/102.5/10
Space & placement4.5/103.0/10
Light & reflections5.0/102.5/10
Purposeful detail4.0/102.0/10
Artistry & character4.0/102.5/10
Materials & effects4.0/102.0/10
Visual integrity6.0/103.0/10

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 Terra

Warm sunset gradients, framing palms and colorful beach activities create an appealing scene. Animals, birds and a sun reflection fulfill the brief. The dog and turtle remain schematic, foreground depth is shallow, and the reflection forms rigid bands. Clean silhouettes and readable accessories support a competent illustration, but limited anatomy, material variation and lighting keep it below exceptional.

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 TerraInkling-Small
Task & likeness7.5/103.5/10
Anatomy & construction5.0/103.0/10
Space & placement6.0/103.0/10
Light & reflections5.0/103.0/10
Purposeful detail6.5/103.0/10
Artistry & character5.0/103.0/10
Materials & effects5.5/102.5/10
Visual integrity5.0/102.0/10

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 Terra

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 Terra

Expressive faces, a recognizable raccoon perched on the dog, and a sweeping wake make an appealing cartoon. The principal weakness is the steering interaction: the dog's paw sits beside the control assembly without a convincing handlebar grip. Bold outlines and coherent layering provide polish, while simplified shading, compressed seating geometry and angular splashes limit depth and physical credibility.

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 TerraInkling-Small
Task & likeness7.5/104.0/10
Anatomy & construction5.0/103.0/10
Space & placement7.0/104.0/10
Light & reflections6.0/105.0/10
Purposeful detail7.0/105.5/10
Artistry & character5.0/104.0/10
Materials & effects7.0/105.0/10
Visual integrity7.5/105.0/10

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-5.6 Terra

The oversized bill, expressive eye and balanced twilight palette make the cyclist immediately readable. Clean contours and wheel details support the illustration, but the rabbit-like head tufts weaken pelican likeness. The wing does not clearly grip the handlebar, pedal contact is uneven, and the drivetrain is incomplete. Lighting remains mostly decorative.

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 TerraInkling-Small
Task & likeness6.0/104.0/10
Anatomy & construction6.0/103.0/10
Space & placement7.0/103.0/10
Light & reflections6.5/103.0/10
Purposeful detail7.0/104.5/10
Artistry & character6.5/105.0/10
Materials & effects6.5/104.5/10
Visual integrity7.0/103.0/10

Benchmark task

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