STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemma 4 31B vs Iceman Contributor

Gemma 4 31B leads Iceman Contributor by 6.6 points on StealthMark, 25.8 to 19.2. It leads on 5 of 9 benchmarks, including both games, and Iceman Contributor on 4. Gemma 4 31B scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

25.8/100Overall rank 44/53
19.2/100Overall rank 47/53

General Intelligence

19.1/100
11.7/100

Visual Intelligence

36.7/100
31.0/100

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
  • Iceman Contributor
  • Other models
  • Median

DATASHEET

Specs and pricing

Gemma 4 31B scores higher on StealthMark and runs 2.5× faster in our speed test.

  • Gemma 4 31B
  • Iceman Contributor
  • Other models
  • Median
PricePer 1M output tokens, input below
Gemma 4 31B: $0.40$0.14 inputIceman Contributor: No list price
Context windowTokens per request, max output below
Gemma 4 31B: 256KIceman Contributor: Not published
Output speedTokens per second, our measurement
Gemma 4 31B: 1162.5× fastertokens/sIceman Contributor: 46tokens/s
SizeTotal and active parameters
Gemma 4 31B: 30.7BAll activeEstimatedIceman Contributor: Not disclosed
Developer
Google DeepMindNot published
Released
2 Apr 2026Not published
Origin
United StatesNot published
Input → output
Text, image → textNot published
Architecture
Dense multimodal transformer with interleaved sliding-window and global attentionNot published

Full datasheets, every price and sourceGemma 4 31B ↗

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

Iceman Contributor 3.2/100Rank 47/47

Survived 0 of 3
Foresight: complete playing field
Level 31 ptsTurn 7 / 20

Points per level

LevelGemma 4 31BIceman Contributor
Level 1Second Thoughts
9 ptsOut of lives
0 ptsOut of lives
Level 2Pressure Pot
6 ptsOut of lives
3 ptsOut of lives
Level 3Hide or Flight
8 ptsOut of lives
1 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

Iceman Contributor 3.6/100Rank 44/48

Cleared 1 of 5
Latch: complete playing field
Level 55 ptsTurn 25 / 40

Points per level

LevelGemma 4 31BIceman Contributor
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9 ptsCleared
2.8 ptsFinished early
Level 3Relay vault
13.2 ptsFinished early
2.2 ptsFinished early
Level 4Passing bay
2.2 ptsFinished early
4 ptsFinished early
Level 5Second thoughts
Not played
5 ptsFinished early

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.

Iceman Contributor

The image provides limited evidence through rounded volume, faint wall strips and floor echoes. Its main sphere is small and low, the paint beads do not establish the required interaction history, and most of the defining mirror structure is missing.

Score breakdown

CategoryGemma 4 31BIceman Contributor
State at 600 ms11.0/250.5/25
Camera and placement3.0/152.5/15
Reflections0.0/1207.5/120
Materials and scale5.5/103.0/10
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.

Iceman Contributor

The crystal crown, cyan eyes and blue faceting communicate an icy fantasy character. Anatomical readability is substantially weaker: the ringed torso, crowded facial construction and fingerless appendages do not resolve the requested childlike crouch or pouncing gesture. Sparse surface detail and shallow shading further limit the result.

Score breakdown

CategoryGemma 4 31BIceman Contributor
Task & likeness6.0/104.0/10
Anatomy & construction6.0/103.0/10
Space & placement7.5/104.0/10
Light & reflections6.5/104.5/10
Purposeful detail5.5/104.0/10
Artistry & character5.0/104.5/10
Materials & effects6.5/104.5/10
Visual integrity7.5/104.0/10

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.

Iceman Contributor

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

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.

Iceman Contributor

The portrait retains a dark silhouette against an earthy landscape, but replication is weak. The frontal body, elongated facial proportions and undifferentiated hands lose the reference's defining pose and likeness. Basic gradients and layered hills provide some coherence, with little anatomical or painterly detail.

Score breakdown

CategoryGemma 4 31BIceman Contributor
Task & likeness3.0/101.5/10
Anatomy & construction4.0/101.5/10
Space & placement4.0/102.5/10
Light & reflections3.5/102.0/10
Purposeful detail2.0/102.0/10
Artistry & character3.5/102.0/10
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

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.

Iceman Contributor

A coherent sunset beach with recognizable animals, playful details and effective palm framing. Connected silhouettes and layered scenery support modest construction and placement credit. Jointless figures, limited foreshortening and an inadequately separated sun and reflection keep the execution basic despite its attractive color.

Score breakdown

CategoryGemma 4 31BIceman Contributor
Task & likeness5.0/107.0/10
Anatomy & construction2.0/103.5/10
Space & placement5.0/106.0/10
Light & reflections2.5/104.0/10
Purposeful detail2.0/105.5/10
Artistry & character2.0/103.5/10
Materials & effects2.0/104.5/10
Visual integrity5.0/105.0/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Different task instructions

Physical reasoning, light and visual reconstruction.

The judgment

Gemma 4 31B

This benchmark has not been assessed yet.

Iceman Contributor

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.

Iceman Contributor

The sunset palette and red hull establish an appealing setting, but the central interaction remains unresolved. Overlapping bodies obscure the dog, supported seating is unclear, and no readable paw-to-control grip demonstrates steering. Simple construction, weak environmental lighting and loosely described spray limit depth and finish.

Score breakdown

CategoryGemma 4 31BIceman Contributor
Task & likeness2.5/102.0/10
Anatomy & construction3.0/103.0/10
Space & placement4.0/103.0/10
Light & reflections1.0/104.0/10
Purposeful detail2.5/103.5/10
Artistry & character2.5/102.5/10
Materials & effects2.0/104.0/10
Visual integrity7.0/102.5/10

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.

Iceman Contributor

A recognizable pelican and bicycle sit within an appealing sunset composition. Feather contours, bill shape and atmospheric colour provide character, but disconnected-looking leg origins, unclear pedal contact and unresolved steering weaken the central riding action. Consistent wheel alignment establishes a side view without resolving the rider's support.

Score breakdown

CategoryGemma 4 31BIceman Contributor
Task & likeness4.0/104.0/10
Anatomy & construction3.0/103.5/10
Space & placement4.5/103.5/10
Light & reflections5.0/105.0/10
Purposeful detail3.0/104.5/10
Artistry & character3.0/103.5/10
Materials & effects4.0/104.0/10
Visual integrity4.5/103.0/10

Benchmark task

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