STEALTHMARK · HEAD TO HEAD

All comparisons ↗

MiMo-V2.6-Pro vs Qwen3.5-9B

MiMo-V2.6-Pro leads Qwen3.5-9B by 37.4 points on StealthMark, 47.9 to 10.5. It leads on all 9 benchmarks. MiMo-V2.6-Pro scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

47.9/100Overall rank 21/53
10.5/100Overall rank 53/53

General Intelligence

44.3/100
7.8/100

Visual Intelligence

54.3/100
14.9/100

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

Open modelMIT
Local modelOpen model · Apache-2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • MiMo-V2.6-Pro
  • Qwen3.5-9B
  • Other models
  • Median

DATASHEET

Specs and pricing

MiMo-V2.6-Pro scores higher on StealthMark. Qwen3.5-9B is 3.5× cheaper per output token and runs 39% faster in our speed test. Both take about 1M tokens of context.

  • MiMo-V2.6-Pro
  • Qwen3.5-9B
  • Other models
  • Median
PricePer 1M output tokens, input below
MiMo-V2.6-Pro: $0.87$0.43 inputQwen3.5-9B: $0.253.5× cheaper$0.17 input
Context windowTokens per request, max output below
MiMo-V2.6-Pro: 1MTied128K max outputQwen3.5-9B: 1.01MTied
Output speedTokens per second, our measurement
MiMo-V2.6-Pro: 116tokens/sQwen3.5-9B: 16139% fastertokens/s
SizeTotal and active parameters
MiMo-V2.6-Pro: 1.02T42B activeQwen3.5-9B: 9BAll activeEstimated
Developer
XiaomiQwen
Released
21 Sep 20262 Mar 2026
Origin
ChinaBoth
Input → output
Text, image, video, audio → textText, image, video → text
Architecture
Sparse Mixture-of-Experts; OpenRouter maps the route to the released Pro-RL checkpoint. The UltraSpeed edition is a separate routeDense causal language model with vision encoder; Gated DeltaNet + gated attention; MTP-trained

Full datasheets, every price and sourceMiMo-V2.6-Pro ↗Qwen3.5-9B ↗

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-Pro 54.6/100Rank 13/47

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

Qwen3.5-9B 12.8/100Rank 43/47

Survived 0 of 3
Foresight: complete playing field
Level 32 ptsTurn 8 / 20

Points per level

LevelMiMo-V2.6-ProQwen3.5-9B
Level 1Second Thoughts
4 ptsOut of lives
4 ptsOut of lives
Level 2Pressure Pot
9 ptsOut of lives
4 ptsOut of lives
Level 3Hide or Flight
19 ptsSurvived
2 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-Pro 52.6/100Rank 22/48

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

Qwen3.5-9B 3.8/100Rank 43/48

Cleared 1 of 5
Latch: complete playing field
Level 54.4 ptsTurn 33 / 40

Points per level

LevelMiMo-V2.6-ProQwen3.5-9B
Level 1Hold the door
5.2 ptsCleared
5 ptsCleared
Level 2Crossfeed
9 ptsClearedFinished early · 1 beacon left
3.8 ptsFinished early
Level 3Relay vault
17.2 ptsClearedFinished early · 1 beacon left
1.2 ptsFinished early
Level 4Passing bay
16 ptsClearedFinished early · 3 beacons left
0.2 ptsFinished early
Level 5Second thoughts
20.4 ptsCleared
4.4 ptsFinished early

Newton's Mirror

Same task instructions

Physics, perspective and recursive reflections, tested together. Explore the test ↗

The judgment

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.

Qwen3.5-9B

Horizontal centering and a separate airborne black blob are visible. Cyan's recent contact and crimson's forward transport are insufficiently demonstrated, while sphere support remains obscured. The enlarged, lowered sphere substantially changes the composition. The wall and floor sphere images, recursive room structure and curved emitter mappings are almost entirely missing.

Score breakdown

CategoryMiMo-V2.6-ProQwen3.5-9B
State at 600 ms23.0/253.0/25
Camera and placement12.0/154.5/15
Reflections19.0/1202.0/120
Materials and scale7.5/103.0/10
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

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.

Qwen3.5-9B

Glowing teal spheres and a harmonious palette provide visible strengths, but the central character remains seriously unresolved. A large gap separates head and torso, limbs cannot be traced, and scattered garment shapes fail to establish the ornate costume. The foreground mound replaces the tall enclosing arch. Clean primitive edges do not repair these construction failures.

Score breakdown

CategoryMiMo-V2.6-ProQwen3.5-9B
Task & likeness6.5/103.0/10
Anatomy & construction5.0/102.0/10
Space & placement5.5/103.0/10
Light & reflections6.5/103.5/10
Purposeful detail6.5/102.0/10
Artistry & character5.0/102.0/10
Materials & effects6.5/104.0/10
Visual integrity6.0/103.0/10

Benchmark task

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.

Qwen3.5-9B

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

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

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.

Qwen3.5-9B

A centered dark oval with sparse facial marks forms a simple graphic face, but scarcely replicates the Mona Lisa. The portrait's body, crossed hands, clothing and landscape are missing, while angular facial construction and flat tones lose its likeness, volume and subtle expression.

Score breakdown

CategoryMiMo-V2.6-ProQwen3.5-9B
Task & likeness3.5/100.0/10
Anatomy & construction3.5/100.0/10
Space & placement4.0/100.0/10
Light & reflections5.0/100.0/10
Purposeful detail3.0/100.0/10
Artistry & character4.0/100.5/10
Materials & effects4.0/100.0/10
Visual integrity6.0/100.5/10

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-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.

Qwen3.5-9B

The beach is recognizable, and sweeping shoreline curves provide basic rhythm. Wildlife and playful activity remain poorly resolved, with ambiguous body construction and object contact. The sun glows without corresponding reflections or surface lighting. Fragmented subjects and an unintegrated rectangular panel substantially weaken composition and finish.

Score breakdown

CategoryMiMo-V2.6-ProQwen3.5-9B
Task & likeness8.5/101.5/10
Anatomy & construction5.0/100.5/10
Space & placement6.0/101.5/10
Light & reflections6.5/101.0/10
Purposeful detail6.5/102.5/10
Artistry & character5.0/101.5/10
Materials & effects6.0/100.5/10
Visual integrity6.0/101.5/10

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

MiMo-V2.6-Pro

This benchmark has not been assessed yet.

Qwen3.5-9B

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-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.

Qwen3.5-9B

Bright colors, clean individual shapes and basic animal cues make the scene partly recognizable. Back seating, body continuity, steering and jet ski construction remain unresolved. Background gradients and wave rhythm provide some finish, but substantial anatomical, spatial and interaction weaknesses dominate.

Score breakdown

CategoryMiMo-V2.6-ProQwen3.5-9B
Task & likeness7.0/102.5/10
Anatomy & construction5.0/101.0/10
Space & placement5.5/102.0/10
Light & reflections5.5/101.0/10
Purposeful detail6.0/101.5/10
Artistry & character4.0/101.0/10
Materials & effects5.5/101.0/10
Visual integrity4.5/102.5/10

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

Same task instructions

Subject construction and spatial relationships.

The judgment

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.

Qwen3.5-9B

The oversized bill and orderly spoked wheels make the subject partly recognizable. Clean contours and strong color contrast provide graphic clarity, but unresolved appendages, steering, drivetrain and support dominate the construction. Sparse shading and detail further limit the illustration.

Score breakdown

CategoryMiMo-V2.6-ProQwen3.5-9B
Task & likeness6.5/104.0/10
Anatomy & construction5.0/101.5/10
Space & placement6.0/103.0/10
Light & reflections5.5/101.5/10
Purposeful detail6.0/102.5/10
Artistry & character6.0/101.5/10
Materials & effects5.5/101.5/10
Visual integrity6.0/102.5/10

Benchmark task

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