STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemma 4 31B vs MiMo-V2.6-Pro

MiMo-V2.6-Pro leads Gemma 4 31B by 22.1 points on StealthMark, 47.9 to 25.8. It leads on 8 of 9 benchmarks, including both games, and Gemma 4 31B on 1. MiMo-V2.6-Pro 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
47.9/100Overall rank 21/53

General Intelligence

19.1/100
44.3/100

Visual Intelligence

36.7/100
54.3/100

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
Open modelMIT

BENCHMARK BY BENCHMARK

Where each model leads

  • Gemma 4 31B
  • MiMo-V2.6-Pro
  • Other models
  • Median

DATASHEET

Specs and pricing

Gemma 4 31B is 2.2× cheaper per output token. MiMo-V2.6-Pro scores higher on StealthMark and takes 4× more context.

  • Gemma 4 31B
  • MiMo-V2.6-Pro
  • Other models
  • Median
PricePer 1M output tokens, input below
Gemma 4 31B: $0.402.2× cheaper$0.14 inputMiMo-V2.6-Pro: $0.87$0.43 input
Context windowTokens per request, max output below
Gemma 4 31B: 256KMiMo-V2.6-Pro: 1M4× larger128K max output
Output speedTokens per second, our measurement
Gemma 4 31B: 116Tiedtokens/sMiMo-V2.6-Pro: 116Tiedtokens/s
SizeTotal and active parameters
Gemma 4 31B: 30.7BAll activeEstimatedMiMo-V2.6-Pro: 1.02T42B active
Developer
Google DeepMindXiaomi
Released
2 Apr 202621 Sep 2026
Origin
United StatesChina
Input → output
Text, image → textText, image, video, audio → text
Architecture
Dense multimodal transformer with interleaved sliding-window and global attentionSparse Mixture-of-Experts; OpenRouter maps the route to the released Pro-RL checkpoint. The UltraSpeed edition is a separate route

Full datasheets, every price and sourceGemma 4 31B ↗MiMo-V2.6-Pro ↗

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

MiMo-V2.6-Pro 54.6/100Rank 13/47

Survived 1 of 3
Foresight: complete playing field
Level 319 ptsTurn 20 / 20

Points per level

LevelGemma 4 31BMiMo-V2.6-Pro
Level 1Second Thoughts
9 ptsOut of lives
4 ptsOut of lives
Level 2Pressure Pot
6 ptsOut of lives
9 ptsOut of lives
Level 3Hide or Flight
8 ptsOut of lives
19 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 39/484 of 5 levels

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

MiMo-V2.6-Pro 52.6/100Rank 22/48

Cleared 5 of 5
Latch: complete playing field
Level 520.4 ptsTurn 28 / 40

Points per level

LevelGemma 4 31BMiMo-V2.6-Pro
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9 ptsCleared
9 ptsClearedFinished early · 1 beacon left
Level 3Relay vault
13.2 ptsFinished early
17.2 ptsClearedFinished early · 1 beacon left
Level 4Passing bay
2.2 ptsFinished early
16 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
Not played
20.4 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.

MiMo-V2.6-Pro

The main framing and visible paint-contact story are well supported. Major optical omissions dominate the result: sparse repetitions, undersized first images, missing outer chains and absent curved nested imagery prevent a coherent mirror-room system. The metallic forms remain convincing in volume but have a soft illustrative finish.

Score breakdown

CategoryGemma 4 31BMiMo-V2.6-Pro
State at 600 ms11.0/2523.0/25
Camera and placement3.0/1512.0/15
Reflections0.0/12019.0/120
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.

MiMo-V2.6-Pro

An appealing rabbit with balanced framing, expressive eyes and purposeful costume accents. Simple frontal construction limits anatomical and spatial accomplishment. The orange orb provides an effective luminous focal point, but unreadable wrist connections weaken the requested gestures and prevent stronger integrity credit.

Score breakdown

CategoryGemma 4 31BMiMo-V2.6-Pro
Task & likeness6.0/106.5/10
Anatomy & construction6.0/105.0/10
Space & placement7.5/105.5/10
Light & reflections6.5/106.5/10
Purposeful detail5.5/106.5/10
Artistry & character5.0/105.0/10
Materials & effects6.5/106.5/10
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.

MiMo-V2.6-Pro

A small rabbit in an explorer outfit floats with a luminous orb. The scene tests character anatomy, pose and the placement of geometric forms around it.

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.

MiMo-V2.6-Pro

The portrait is recognizable through its dark silhouette, slight smile and muted landscape, but replication is weak. A frontal, oversized head and symmetric torso replace the reference's turned seated pose; angular, separated hands omit its central gesture. Smooth shading maintains coherence while anatomical detail, depth and material rendering remain basic.

Score breakdown

CategoryGemma 4 31BMiMo-V2.6-Pro
Task & likeness3.0/103.5/10
Anatomy & construction4.0/103.5/10
Space & placement4.0/104.0/10
Light & reflections3.5/105.0/10
Purposeful detail2.0/103.0/10
Artistry & character3.5/104.0/10
Materials & effects2.5/104.0/10
Visual integrity5.5/106.0/10

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.

MiMo-V2.6-Pro

A readable sunset beach with clear requested subjects, appealing framing and purposeful accessories. Schematic anatomy, flattened foreground objects, repetitive water highlights and sparse directional shadows limit construction and physical depth. The kite's unresolved anchor also constrains integrity.

Score breakdown

CategoryGemma 4 31BMiMo-V2.6-Pro
Task & likeness5.0/108.5/10
Anatomy & construction2.0/105.0/10
Space & placement5.0/106.0/10
Light & reflections2.5/106.5/10
Purposeful detail2.0/106.5/10
Artistry & character2.0/105.0/10
Materials & effects2.0/106.0/10
Visual integrity5.0/106.0/10

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.

MiMo-V2.6-Pro

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.

MiMo-V2.6-Pro

A coherent, cheerful cartoon with recognizable animals, readable steering contact and useful small details. The dog's orientation follows the craft more successfully than a wholly frontal pose would. Simple anatomy, weak raccoon grip and compressed seating contacts still limit physical credibility. Gradients and spray provide polish without resolving complex construction.

Score breakdown

CategoryGemma 4 31BMiMo-V2.6-Pro
Task & likeness2.5/107.0/10
Anatomy & construction3.0/105.0/10
Space & placement4.0/105.5/10
Light & reflections1.0/105.5/10
Purposeful detail2.5/106.0/10
Artistry & character2.5/104.0/10
Materials & effects2.0/105.5/10
Visual integrity7.0/104.5/10

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

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.

MiMo-V2.6-Pro

The distinctive bill, continuous silhouette and detailed wheels establish a readable pelican cyclist. Shaped feathers and soft shading add character, but jointless legs, crowded pedal contacts, absent steering contact and loosely directional lighting limit the construction. The comparisons support retaining the baseline category scores.

Score breakdown

CategoryGemma 4 31BMiMo-V2.6-Pro
Task & likeness4.0/106.5/10
Anatomy & construction3.0/105.0/10
Space & placement4.5/106.0/10
Light & reflections5.0/105.5/10
Purposeful detail3.0/106.0/10
Artistry & character3.0/106.0/10
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.