STEALTHMARK · HEAD TO HEAD

All comparisons ↗

MiMo-V2.6-Flash vs Qwen4-Max-Preview

Qwen4-Max-Preview leads MiMo-V2.6-Flash by 9.5 points on StealthMark, 58.8 to 49.3. It leads on 8 of 9 benchmarks, including both games, and MiMo-V2.6-Flash on 1. Qwen4-Max-Preview scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

49.3/100Overall rank 23/58
58.8/100Overall rank 12/58

General Intelligence

45.5/100
54.6/100

Visual Intelligence

54.7/100
66.3/100

Reasoning efficiency

How many reasoning tokens a model needs for the quality it delivers.

Single-step reasoning How much it reasons to understand a task

Multi-step reasoning How much it keeps reasoning as a task goes on

Cost efficiency

How much Performance you get for your money.

  • Qwen4-Max-PreviewNot measured

Open or local

Open modelMIT

BENCHMARK BY BENCHMARK

Where each model leads

  • MiMo-V2.6-Flash
  • Qwen4-Max-Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

MiMo-V2.6-Flash runs 8.3× faster in our speed test. Qwen4-Max-Preview scores higher on StealthMark.

  • MiMo-V2.6-Flash
  • Qwen4-Max-Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
MiMo-V2.6-Flash: $0.28$0.14 inputQwen4-Max-Preview: No list price
Context windowTokens per request, max output below
MiMo-V2.6-Flash: 1M128K max outputQwen4-Max-Preview: Not published
Output speedTokens per second, our measurement
MiMo-V2.6-Flash: 5478.3× fastertokens/sQwen4-Max-Preview: 66tokens/s
SizeTotal and active parameters
MiMo-V2.6-Flash: 309B15B activeQwen4-Max-Preview: Not disclosed
Developer
XiaomiNot published
Released
21 Sep 2026Not published
Origin
ChinaNot published
Input → output
Text, image, video, audio → textNot published
Architecture
Released Flash-RL checkpoint: sparse Mixture-of-Experts; hosted Flash and MOPD variants are distinct artifactsNot published

Full datasheets, every price and sourceMiMo-V2.6-Flash ↗

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.

MiMo-V2.6-Flash 71.3/100Rank 42/541 of 3 levels

1 of 3 played
Foresight: complete playing field
Level 212 ptsTurn 14 / 18

Qwen4-Max-Preview 57.5/100Rank 14/54

Survived 1 of 3
Foresight: complete playing field
Level 310 ptsTurn 15 / 20

Points per level

LevelMiMo-V2.6-FlashQwen4-Max-Preview
Level 1Second Thoughts
Pending
20 ptsSurvived
Level 2Pressure Pot
12 ptsOut of lives
12 ptsOut of lives
Level 3Hide or Flight
Not played
10 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.

MiMo-V2.6-Flash 66.3/100Rank 34/553 of 5 levels

3 of 5 played
Latch: complete playing field
Level 318 ptsTurn 36 / 36

Qwen4-Max-Preview 67.3/100Rank 21/55

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

Points per level

LevelMiMo-V2.6-FlashQwen4-Max-Preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
8.8 ptsClearedFinished early · 1 beacon left
Level 3Relay vault
18 ptsCleared
19.2 ptsCleared
Level 4Passing bay
Pending
17.2 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

MiMo-V2.6-Flash

The main sphere's scale, approximate placement and separate airborne black are supported. The colored beads do not establish the required paint history. Plausible locations for three reflected silhouettes provide limited optical credit, while missing chains, nested imagery and coherent emitter mapping dominate the assessment.

Qwen4-Max-Preview

The main placement, compact airborne black and contrasting cyan/crimson interaction states are largely supported. Recognizable first mirror images earn substantial local credit despite modest silhouette and overlap errors. Most of the defining mirror system remains missing, especially nested spherical imagery, outer chains and repeated emitter mapping. Crimson also extends slightly too far down the facing surface.

Score breakdown

CategoryMiMo-V2.6-FlashQwen4-Max-Preview
State at 600 ms13.0/2524.5/25
Camera and placement12.0/1514.0/15
Reflections15.5/12039.0/120
Materials and scale7.5/106.5/10
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

MiMo-V2.6-Flash

The centered rabbit has an appealing alert expression, a balanced silhouette, and a restrained technological palette. Outfit panels and orbital accents are cleanly resolved. The orb-holding paw has an ambiguous grip, the ears lack distinct angular bends, and the halo's interlocking construction is unclear. Soft shading suggests volume, but materials and spatial depth remain simplified.

Qwen4-Max-Preview

A coherent celestial character with readable costume layers, controlled ornament and coordinated luminous accents. Simplified joints, shallow frontal space and limited material modeling constrain construction and drawing complexity. The raised palm's orientation remains only partially demonstrated.

Score breakdown

CategoryMiMo-V2.6-FlashQwen4-Max-Preview
Task & likeness8.0/108.5/10
Anatomy & construction6.5/107.5/10
Space & placement7.0/107.5/10
Light & reflections7.0/107.0/10
Purposeful detail6.0/108.0/10
Artistry & character5.5/107.5/10
Materials & effects6.5/106.5/10
Visual integrity8.0/107.5/10

Benchmark task

MiMo-V2.6-Flash

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.

Qwen4-Max-Preview

A floating capybara in ornate robes tests character anatomy, layered fabric and the placement of surrounding luminous forms.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

MiMo-V2.6-Flash

The dark clothing, long hair, folded hands and hazy landscape make the reference recognizable. Replication is limited by the frontal symmetry, elongated face, wide staring eyes and downturned mouth. Both arms connect to the hands, but the overlapping palms and looplike fingers are poorly resolved. Soft facial shading provides some volume; the clothing and landscape remain broad, simplified shapes.

Qwen4-Max-Preview

A coherent, recognizable interpretation with developed facial shading and purposeful portrait details. The frontal, nearly symmetric body, inflated sleeves and unresolved hand articulation substantially limit replication and construction. Layered scenery supplies basic depth, while uniformly smooth surfaces and schematic folds constrain material character and drawing complexity.

Score breakdown

CategoryMiMo-V2.6-FlashQwen4-Max-Preview
Task & likeness3.0/104.5/10
Anatomy & construction3.0/105.5/10
Space & placement4.0/105.0/10
Light & reflections3.0/106.5/10
Purposeful detail4.0/106.0/10
Artistry & character3.0/105.5/10
Materials & effects3.5/105.0/10
Visual integrity5.5/105.5/10

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

MiMo-V2.6-Flash

The warm sunset, aligned reflection, framing palms and playful beach animals create an appealing, coherent scene. Small toys and shells remain readable. Drawing is simplified: animals have limited volume, water uses repetitive horizontal strokes, and foreground shadows do not consistently follow the central sun. Clean execution supports a competent illustration, but depth and material rendering remain modest.

Qwen4-Max-Preview

A coherent sunset illustration with sweeping palms, recognizable wildlife and varied, readable beach details. Atmospheric layering and controlled contours strengthen its character. Basic animal anatomy, overhead-looking foreground creatures and schematic cast shadows limit construction and physical depth.

Score breakdown

CategoryMiMo-V2.6-FlashQwen4-Max-Preview
Task & likeness7.5/108.5/10
Anatomy & construction6.5/108.0/10
Space & placement7.0/106.5/10
Light & reflections6.0/107.5/10
Purposeful detail7.0/108.0/10
Artistry & character6.0/108.5/10
Materials & effects6.0/106.5/10
Visual integrity8.0/107.0/10

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

MiMo-V2.6-Flash

This benchmark has not been assessed yet.

Qwen4-Max-Preview

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

MiMo-V2.6-Flash

The raccoon riding the dog reads clearly, with expressive faces and a cheerful waterscape. The steering action is weak: no paw reaches the handlebar, which meets the dog's muzzle. The vehicle resembles a thin board with a steering post. Overlapping limbs obscure anatomy, while limited shadows, reflections and surface modeling keep the scene flat.

Qwen4-Max-Preview

An expressive cartoon with purposeful accessory detail, readable steering and directional spray. The aligned sunset reflection adds physical coherence. Simplified joints and the frontal raccoon's uncertain seated support continue to limit anatomy, perspective and integrity.

Score breakdown

CategoryMiMo-V2.6-FlashQwen4-Max-Preview
Task & likeness6.5/108.0/10
Anatomy & construction4.0/107.5/10
Space & placement6.5/106.0/10
Light & reflections4.5/106.5/10
Purposeful detail5.5/108.0/10
Artistry & character4.0/106.5/10
Materials & effects5.5/107.0/10
Visual integrity6.0/106.0/10

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

MiMo-V2.6-Flash

The pelican is immediately recognizable, with an expressive eye and prominent pouch, and the landscape provides clear framing. Clean outlines and spokes support the cheerful illustration. Both feet visibly miss the bicycle's pedal mechanism, weakening the riding action. Simplified machinery, shallow depth and loosely directional shading limit the requested masterpiece quality.

Qwen4-Max-Preview

A detailed coastal illustration with readable seated support, steering and pedal contacts. Continuous anatomy, coherent bicycle construction and purposeful small features support its expressive composition. Simplified limb articulation, modest perspective depth and weakly directional ground shadows limit physical conviction.

Score breakdown

CategoryMiMo-V2.6-FlashQwen4-Max-Preview
Task & likeness8.0/108.5/10
Anatomy & construction5.5/108.0/10
Space & placement7.0/107.5/10
Light & reflections6.0/106.5/10
Purposeful detail7.0/108.0/10
Artistry & character6.5/107.5/10
Materials & effects5.5/107.0/10
Visual integrity7.5/108.0/10

Benchmark task

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