STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemma 4 31B vs Muse Wonder

Muse Wonder leads Gemma 4 31B by 31.2 points on StealthMark, 57.0 to 25.8. It leads on all 9 benchmarks. Muse Wonder scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

25.8/100Overall rank 44/53
57.0/100Overall rank 10/53

General Intelligence

19.1/100
53.1/100

Visual Intelligence

36.7/100
64.0/100

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

Open or local

Local modelOpen model · Apache 2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Gemma 4 31B
  • Muse Wonder
  • Other models
  • Median

DATASHEET

Specs and pricing

Gemma 4 31B is 50× cheaper per output token. Muse Wonder scores higher on StealthMark, takes 4× more context and runs 4.9× faster in our speed test.

  • Gemma 4 31B
  • Muse Wonder
  • Other models
  • Median
PricePer 1M output tokens, input below
Gemma 4 31B: $0.4050× cheaper$0.14 inputMuse Wonder: $20$4 input
Context windowTokens per request, max output below
Gemma 4 31B: 256KMuse Wonder: 1M4× larger
Output speedTokens per second, our measurement
Gemma 4 31B: 116tokens/sMuse Wonder: 5704.9× fastertokens/s
SizeTotal and active parameters
Gemma 4 31B: 30.7BAll activeEstimatedMuse Wonder: Not disclosed
Developer
Google DeepMindMeta
Released
2 Apr 202612 Oct 2026
Origin
United StatesBoth
Input → output
Text, image → textText, image, video, audio, PDF → text
Architecture
Dense multimodal transformer with interleaved sliding-window and global attentionNot published

Full datasheets, every price and sourceGemma 4 31B ↗Muse Wonder ↗

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 30/47

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

Muse Wonder 52.3/100Rank 17/47

Survived 0 of 3
Foresight: complete playing field
Level 311 ptsTurn 17 / 20

Points per level

LevelGemma 4 31BMuse Wonder
Level 1Second Thoughts
9 ptsOut of lives
16 ptsOut of lives
Level 2Pressure Pot
6 ptsOut of lives
10 ptsOut of lives
Level 3Hide or Flight
8 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.

Gemma 4 31B 26.6/100Rank 39/484 of 5 levels

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

Muse Wonder 67.0/100Rank 17/48

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

Points per level

LevelGemma 4 31BMuse Wonder
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9 ptsCleared
9 ptsCleared
Level 3Relay vault
13.2 ptsFinished early
18.8 ptsCleared
Level 4Passing bay
2.2 ptsFinished early
17.8 ptsClearedFinished early · 1 beacon left
Level 5Second thoughts
Not played
20.6 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.

Muse Wonder

The flattened cyan cap, separate airborne black blob and crimson droplets support much of the contact sequence, although crimson adhesion and forward carriage remain unresolved. Main-sphere placement is broadly compatible with the prescribed view. Sparse isolated mirror images replace the defining repeated room structure and curved nested reflections. The crimson mass is visibly oversized, and the top-center lamp image is missing.

Score breakdown

CategoryGemma 4 31BMuse Wonder
State at 600 ms11.0/2522.0/25
Camera and placement3.0/1512.0/15
Reflections0.0/12021.5/120
Materials and scale5.5/107.5/10
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

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.

Muse Wonder

An appealing, coherent cartoon with a readable effortful expression and clear forefeet gripping the trunk. Soft colours and controlled contours support its tenderness. Smooth ears, stiff foreleg construction, limited surface texture and uncertain seed contact keep the execution below intricate illustration quality.

Score breakdown

CategoryGemma 4 31BMuse Wonder
Task & likeness6.0/107.5/10
Anatomy & construction6.0/107.0/10
Space & placement7.5/107.5/10
Light & reflections6.5/107.0/10
Purposeful detail5.5/107.5/10
Artistry & character5.0/106.5/10
Materials & effects6.5/106.5/10
Visual integrity7.5/108.0/10

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.

Muse Wonder

A small elephant protecting a delicate seed tests expressive anatomy, physical contact and contrasting organic materials.

Mona Lisa

Different 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.

Muse Wonder

A competent illustrative interpretation with controlled curves, readable details and coherent depth layers. Facial, hair and garment shading demonstrate more development than basic construction. Replication remains limited by the frontal pose, elongated face and pronounced smile; crowded fingers, weak contact shadows and smooth materials constrain anatomical and painterly conviction.

Score breakdown

CategoryGemma 4 31BMuse Wonder
Task & likeness3.0/105.5/10
Anatomy & construction4.0/105.5/10
Space & placement4.0/105.5/10
Light & reflections3.5/105.5/10
Purposeful detail2.0/105.5/10
Artistry & character3.5/105.5/10
Materials & effects2.5/105.0/10
Visual integrity5.5/106.5/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Different 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.

Muse Wonder

A lively beach illustration with expressive animals, controlled colour transitions and unusually readable accessories. Connected graphic forms make the activities recognizable. Crowded overlaps, compressed depth, schematic joints, weak directional shadows and limited material variation constrain its physical coherence and refinement.

Score breakdown

CategoryGemma 4 31BMuse Wonder
Task & likeness5.0/108.5/10
Anatomy & construction2.0/106.0/10
Space & placement5.0/106.5/10
Light & reflections2.5/106.5/10
Purposeful detail2.0/109.0/10
Artistry & character2.0/107.0/10
Materials & effects2.0/106.0/10
Visual integrity5.0/107.0/10

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.

Muse Wonder

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

Different 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.

Muse Wonder

An expressive, coherent cartoon demonstrates the requested riding and steering interaction. Clean contours, differentiated accessories and energetic spray support its appeal. Concealed seated contacts, compressed vehicle perspective and weak directional lighting limit physical resolution despite the detailed presentation.

Score breakdown

CategoryGemma 4 31BMuse Wonder
Task & likeness2.5/107.5/10
Anatomy & construction3.0/105.5/10
Space & placement4.0/106.5/10
Light & reflections1.0/104.5/10
Purposeful detail2.5/107.5/10
Artistry & character2.5/105.5/10
Materials & effects2.0/107.0/10
Visual integrity7.0/107.0/10

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

Different 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.

Muse Wonder

A controlled, expressive seaside illustration with a distinctive pelican, coherent bicycle geometry and successfully resolved graphic detail. Visible pedal support and plausible occlusion strengthen the riding construction. Aligned wheels and layered scenery establish placement. Limited cast shadows, simplified leg articulation and restrained material modeling constrain its physical finish.

Score breakdown

CategoryGemma 4 31BMuse Wonder
Task & likeness4.0/108.5/10
Anatomy & construction3.0/106.0/10
Space & placement4.5/107.5/10
Light & reflections5.0/105.5/10
Purposeful detail3.0/108.5/10
Artistry & character3.0/107.5/10
Materials & effects4.0/106.0/10
Visual integrity4.5/108.0/10

Benchmark task

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