STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemma 4 31B vs Inkling-Small

Inkling-Small leads Gemma 4 31B by 1.8 points on StealthMark, 27.6 to 25.8. It leads on 6 of 9 benchmarks, including Latch, and Gemma 4 31B on 2, with 1 tied. Inkling-Small scores higher on Ground Truth.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

25.8/100Overall rank 44/53
27.6/100Overall rank 43/53

General Intelligence

19.1/100
25.5/100

Visual Intelligence

36.7/100
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

  • Inkling-Small

Open or local

Local modelOpen model · Apache 2.0
Open modelApache 2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Gemma 4 31B
  • Inkling-Small
  • Other models
  • Median

DATASHEET

Specs and pricing

Inkling-Small scores higher on StealthMark and takes 4× more context.

  • Gemma 4 31B
  • Inkling-Small
  • Other models
  • Median
PricePer 1M output tokens, input below
Gemma 4 31B: $0.40$0.14 inputInkling-Small: No list price
Context windowTokens per request, max output below
Gemma 4 31B: 256KInkling-Small: 1M4× larger
Output speedTokens per second, our measurement
Gemma 4 31B: 116tokens/sInkling-Small: Not measured
SizeTotal and active parameters
Gemma 4 31B: 30.7BAll activeEstimatedInkling-Small: 276B12B active
Developer
Google DeepMindThinking Machines Lab
Released
2 Apr 2026Not published
Origin
United StatesNot published
Input → output
Text, image → textText, image, audio → text
Architecture
Dense multimodal transformer with interleaved sliding-window and global attention42-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 sourceGemma 4 31B ↗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.

Gemma 4 31B 30.2/100Rank 29/49

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 15 / 20

Inkling-Small 30.2/100Rank 29/49

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

Points per level

LevelGemma 4 31BInkling-Small
Level 1Second Thoughts
9 ptsOut of lives
9 ptsOut of lives
Level 2Pressure Pot
6 ptsOut of lives
6 ptsOut of lives
Level 3Hide or Flight
8 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.

Gemma 4 31B 26.6/100Rank 41/504 of 5 levels

4 of 5 played
Latch: complete playing field
Level 42.2 ptsTurn 39 / 40

Inkling-Small 34.7/100Rank 34/50

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

Points per level

LevelGemma 4 31BInkling-Small
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9 ptsCleared
9.8 ptsCleared
Level 3Relay vault
13.2 ptsFinished early
2.8 ptsFinished early
Level 4Passing bay
2.2 ptsFinished early
8 ptsFinished early
Level 5Second thoughts
Not played
18 ptsCleared

Newton's Mirror

Same task instructions

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

The judgment

Gemma 4 31B

The sphere's volume, separate airborne black blob and vertical color ordering are readable. The large, low sphere, plain surrounding planes and absent nested optical imagery leave the central geometric and reflection requirements unsupported. Paint contact and transport remain unresolved. Material credit recognizes the visible convex shading, highlights and distinct surface colors while retaining deductions for the schematic finish and oversized blobs.

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

CategoryGemma 4 31BInkling-Small
State at 600 ms11.0/2514.0/25
Camera and placement3.0/153.0/15
Reflections0.0/1208.0/120
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

Gemma 4 31B

A clean, appealing luminous mascot with coherent body continuity and a readable jar-hugging pose. Rounded highlights, smooth gradients and balanced framing work well. The teardrop silhouette, modest eyes and nearly even grin only partly satisfy the character brief; sparse jar construction and simple geometry limit sophistication.

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

CategoryGemma 4 31BInkling-Small
Task & likeness6.0/102.5/10
Anatomy & construction6.0/101.5/10
Space & placement7.5/103.5/10
Light & reflections6.5/103.0/10
Purposeful detail5.5/104.5/10
Artistry & character5.0/103.0/10
Materials & effects6.5/103.5/10
Visual integrity7.5/102.0/10

Benchmark task

Gemma 4 31B

A small luminous creature proudly holding an empty glass jar tests expression, transparent materials and the balance of character and prop.

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

Gemma 4 31B

The portrait is recognizable through its silhouette, palette and smile, with clean execution of simple shapes. Replication remains weak: the face and pose differ markedly, hands become fingerless ovals, clothing lacks construction, and the landscape loses its atmospheric detail. Basic gradients provide limited volume.

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

CategoryGemma 4 31BInkling-Small
Task & likeness3.0/102.5/10
Anatomy & construction4.0/102.5/10
Space & placement4.0/103.0/10
Light & reflections3.5/102.5/10
Purposeful detail2.0/102.0/10
Artistry & character3.5/102.5/10
Materials & effects2.5/102.0/10
Visual integrity5.5/103.0/10

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

Gemma 4 31B

A coherent beach illustration with clean silhouettes, a sweeping shoreline and an effective sunset palette. Requested subjects are recognizable, but primitive animal construction, sparse detail, unsupported palm placement and schematic reflections limit drawing sophistication and physical credibility.

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

CategoryGemma 4 31BInkling-Small
Task & likeness5.0/103.5/10
Anatomy & construction2.0/103.0/10
Space & placement5.0/103.0/10
Light & reflections2.5/103.0/10
Purposeful detail2.0/103.0/10
Artistry & character2.0/103.0/10
Materials & effects2.0/102.5/10
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

Gemma 4 31B

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

Gemma 4 31B

Clean, simple silhouettes communicate a raccoon riding on a dog. Limited animal specificity, absent steering controls and a flat platform weaken the requested scene. Small facial marks provide purposeful detail, while unresolved support, flat lighting and schematic water restrict physical coherence. Primitive but coherent construction supports basic drawing quality.

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

CategoryGemma 4 31BInkling-Small
Task & likeness2.5/104.0/10
Anatomy & construction3.0/103.0/10
Space & placement4.0/104.0/10
Light & reflections1.0/105.0/10
Purposeful detail2.5/105.5/10
Artistry & character2.5/104.0/10
Materials & effects2.0/105.0/10
Visual integrity7.0/105.0/10

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

Gemma 4 31B

A clean, readable illustration with balanced placement and coherent basic geometry. The sky gradient and ground shadow establish diffuse illumination. Primitive shapes and sparse detail limit artistry, while unclear leg attachment, missing pedal contact and unresolved steering weaken the riding action.

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

CategoryGemma 4 31BInkling-Small
Task & likeness4.0/104.0/10
Anatomy & construction3.0/103.0/10
Space & placement4.5/103.0/10
Light & reflections3.0/103.0/10
Purposeful detail3.0/104.5/10
Artistry & character3.0/105.0/10
Materials & effects4.0/104.5/10
Visual integrity4.5/103.0/10

Benchmark task

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