STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemma 4 31B vs GPT-6.1 Terra

GPT-6.1 Terra leads Gemma 4 31B by 34.6 points on StealthMark, 60.4 to 25.8. It leads on all 9 benchmarks. GPT-6.1 Terra 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 45/54
60.4/100Overall rank 9/54

General Intelligence

19.1/100
58.0/100

Visual Intelligence

36.7/100
64.9/100

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
  • GPT-6.1 Terra
  • Other models
  • Median

DATASHEET

Specs and pricing

Gemma 4 31B is 13× cheaper per output token. GPT-6.1 Terra scores higher on StealthMark and takes 4× more context.

  • Gemma 4 31B
  • GPT-6.1 Terra
  • Other models
  • Median
PricePer 1M output tokens, input below
Gemma 4 31B: $0.4013× cheaper$0.14 inputGPT-6.1 Terra: $5$1 input
Context windowTokens per request, max output below
Gemma 4 31B: 256KGPT-6.1 Terra: 1.05M4× larger128K max output
Output speedTokens per second, our measurement
Gemma 4 31B: 116tokens/sGPT-6.1 Terra: Not measured
SizeTotal and active parameters
Gemma 4 31B: 30.7BAll activeEstimatedGPT-6.1 Terra: Not disclosed
Developer
Google DeepMindOpenAI
Released
2 Apr 202626 Oct 2026
Origin
United StatesBoth
Input → output
Text, image → textBoth
Architecture
Dense multimodal transformer with interleaved sliding-window and global attentionNot published

Full datasheets, every price and sourceGemma 4 31B ↗GPT-6.1 Terra ↗

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 30/50

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

GPT-6.1 Terra 62.0/100Rank 9/50

Survived 2 of 3
Foresight: complete playing field
Level 315 ptsTurn 20 / 20

Points per level

LevelGemma 4 31BGPT-6.1 Terra
Level 1Second Thoughts
9 ptsOut of lives
21 ptsSurvived
Level 2Pressure Pot
6 ptsOut of lives
9 ptsOut of lives
Level 3Hide or Flight
8 ptsOut of lives
15 ptsSurvived

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 42/514 of 5 levels

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

GPT-6.1 Terra 77.7/100Rank 12/51

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

Points per level

LevelGemma 4 31BGPT-6.1 Terra
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9 ptsCleared
9.8 ptsCleared
Level 3Relay vault
13.2 ptsFinished early
19.2 ptsCleared
Level 4Passing bay
2.2 ptsFinished early
17.8 ptsClearedFinished early · 3 beacons 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.

GPT-6.1 Terra

The sphere, airborne black and first reflected silhouettes preserve important geometry within the portrait frame. Paint deformation, contact order and forward transport are supported, with a small crimson endpoint overshoot. Major optical omissions dominate: short finite reflection sequences and smooth bands replace extensive, spatially ordered mirror imagery. Dark gloss and crisp upper emitter shapes provide partial material credit.

Score breakdown

CategoryGemma 4 31BGPT-6.1 Terra
State at 600 ms11.0/2523.0/25
Camera and placement3.0/1511.0/15
Reflections0.0/12033.0/120
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.

GPT-6.1 Terra

A balanced serpent emblem with six attached outward heads, delicate scales and softly rounded bodies. Its compact silhouette reads clearly, but central routing does not establish every alternating crossing or crisp inward corner. Repetitive texture, limited facial anatomy and weak contact shadows constrain its organic character.

Score breakdown

CategoryGemma 4 31BGPT-6.1 Terra
Task & likeness6.0/107.5/10
Anatomy & construction6.0/106.5/10
Space & placement7.5/106.5/10
Light & reflections6.5/106.0/10
Purposeful detail5.5/106.5/10
Artistry & character5.0/106.5/10
Materials & effects6.5/106.0/10
Visual integrity7.5/106.0/10

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.

GPT-6.1 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.

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.

GPT-6.1 Terra

A recognizable interpretation with developed facial shading, shaped sleeve folds and purposeful small features. These strengths support modest upward calibration, while the frontal torso, elongated proportions, schematic finger joints and unresolved seated support keep replication and construction uneven.

Score breakdown

CategoryGemma 4 31BGPT-6.1 Terra
Task & likeness3.0/105.5/10
Anatomy & construction4.0/106.5/10
Space & placement4.0/104.5/10
Light & reflections3.5/106.5/10
Purposeful detail2.0/106.0/10
Artistry & character3.5/106.0/10
Materials & effects2.5/106.0/10
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

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.

GPT-6.1 Terra

A coherent sunset illustration with clear prompt fulfillment, controlled framing and varied, purposeful small details. Simplified joints, frontal staging, flattened animal forms and weakly directional shadows limit its anatomical, spatial and physical sophistication.

Score breakdown

CategoryGemma 4 31BGPT-6.1 Terra
Task & likeness5.0/108.5/10
Anatomy & construction2.0/107.5/10
Space & placement5.0/106.5/10
Light & reflections2.5/105.5/10
Purposeful detail2.0/107.5/10
Artistry & character2.0/107.0/10
Materials & effects2.0/106.5/10
Visual integrity5.0/107.5/10

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.

GPT-6.1 Terra

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.

GPT-6.1 Terra

A coherent cartoon with expressive animals, readable steering and a clear wake. Fine facial and hull details reward inspection. The main limits are the boatlike craft, simplified joints, weakly braced frontal raccoon and minimal directional lighting or material depth.

Score breakdown

CategoryGemma 4 31BGPT-6.1 Terra
Task & likeness2.5/106.5/10
Anatomy & construction3.0/105.5/10
Space & placement4.0/106.0/10
Light & reflections1.0/105.0/10
Purposeful detail2.5/107.0/10
Artistry & character2.5/106.0/10
Materials & effects2.0/106.0/10
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

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.

GPT-6.1 Terra

A coherent pelican cyclist with expressive proportions, purposeful feather detail and developed bicycle machinery. Continuous body contours, aligned wheels and readable pedal contacts support the scene. Simplified articulation, shallow modelling and an unresolved steering connection limit construction and placement.

Score breakdown

CategoryGemma 4 31BGPT-6.1 Terra
Task & likeness4.0/107.0/10
Anatomy & construction3.0/107.0/10
Space & placement4.5/106.0/10
Light & reflections3.0/105.5/10
Purposeful detail3.0/107.0/10
Artistry & character3.0/106.5/10
Materials & effects4.0/105.5/10
Visual integrity4.5/106.0/10

Benchmark task

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