STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6 Astra vs MiMo-V2.6-Flash

GPT-6 Astra leads MiMo-V2.6-Flash by 25.3 points on StealthMark, 74.6 to 49.3. It leads on all 9 benchmarks. GPT-6 Astra scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

74.6/100Overall rank 2/58
49.3/100Overall rank 23/58

General Intelligence

73.4/100
45.5/100

Visual Intelligence

76.9/100
54.7/100

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

  • GPT-6 Astra

Cost efficiency

How much Performance you get for your money.

Open or local

Open modelMIT

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6 Astra
  • MiMo-V2.6-Flash
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-6 Astra scores higher on StealthMark. MiMo-V2.6-Flash is 179× cheaper per output token and runs 8.4× faster in our speed test. Both take about 1.05M tokens of context.

  • GPT-6 Astra
  • MiMo-V2.6-Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6 Astra: $50$10 inputMiMo-V2.6-Flash: $0.28179× cheaper$0.14 input
Context windowTokens per request, max output below
GPT-6 Astra: 1.05MTied128K max outputMiMo-V2.6-Flash: 1MTied128K max output
Output speedTokens per second, our measurement
GPT-6 Astra: 65tokens/sMiMo-V2.6-Flash: 5478.4× fastertokens/s
SizeTotal and active parameters
GPT-6 Astra: Not disclosedMiMo-V2.6-Flash: 309B15B active
Developer
OpenAIXiaomi
Released
3 Sep 202621 Sep 2026
Origin
United StatesChina
Input → output
Text, image → textText, image, video, audio → text
Architecture
Not publishedReleased Flash-RL checkpoint: sparse Mixture-of-Experts; hosted Flash and MOPD variants are distinct artifacts

Full datasheets, every price and sourceGPT-6 Astra ↗MiMo-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.

GPT-6 Astra 76.1/100Rank 3/54

Survived 3 of 3
Foresight: complete playing field
Level 318 ptsTurn 20 / 20

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

Points per level

LevelGPT-6 AstraMiMo-V2.6-Flash
Level 1Second Thoughts
27 ptsSurvived
Pending
Level 2Pressure Pot
11 ptsSurvived
12 ptsOut of lives
Level 3Hide or Flight
18 ptsSurvived
Not played

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.

GPT-6 Astra 87.6/100Rank 2/55

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

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

Points per level

LevelGPT-6 AstraMiMo-V2.6-Flash
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
10.2 ptsClearedFinished early · 1 beacon left
9.6 ptsCleared
Level 3Relay vault
19.2 ptsCleared
18 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
Pending
Level 5Second thoughts
20.6 ptsCleared
Not played

Newton's Mirror

Same task instructions

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

The judgment

GPT-6 Astra

Major placement and the visible contact sequence are convincing. Dense planar light repetition, recognizable spherical panel images and simplified nested sphere motifs provide useful optical structure. Missing outer chains, truncated distant sequences and incorrect bead-like belts still leave the recursive reflections substantially incomplete.

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.

Score breakdown

CategoryGPT-6 AstraMiMo-V2.6-Flash
State at 600 ms25.0/2513.0/25
Camera and placement15.0/1512.0/15
Reflections70.0/12015.5/120
Materials and scale10.0/107.5/10
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

GPT-6 Astra

The sixfold silhouette, pale coloring, outward heads and central hexagon closely match the brief. Fine scales and soft shading support rounded volume. However, several crossings have conspicuous rectangular seams and weak contact shadows, making the weave feel assembled. Small heads have limited anatomical definition, and the repetitive texture conveys less organic life than requested.

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.

Score breakdown

CategoryGPT-6 AstraMiMo-V2.6-Flash
Task & likeness9.0/108.0/10
Anatomy & construction8.0/106.5/10
Space & placement7.5/107.0/10
Light & reflections7.0/107.0/10
Purposeful detail8.0/106.0/10
Artistry & character8.5/105.5/10
Materials & effects8.0/106.5/10
Visual integrity8.5/108.0/10

Benchmark task

GPT-6 Astra

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.

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.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

GPT-6 Astra

Controlled hair contours, neckline detail, modeled sleeves and a layered river landscape give this recognizable portrait developed illustrative finish. The elongated face, largely frontal torso, crowded fingers and weakly established chair support limit replication, anatomical precision and spatial conviction. Small construction slips at the neck and jaw, a stray dark shape under the right cuff and an abruptly ending armrest bar weaken integrity.

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.

Score breakdown

CategoryGPT-6 AstraMiMo-V2.6-Flash
Task & likeness6.5/103.0/10
Anatomy & construction6.5/103.0/10
Space & placement6.5/104.0/10
Light & reflections6.5/103.0/10
Purposeful detail6.5/104.0/10
Artistry & character7.0/103.0/10
Materials & effects7.0/103.5/10
Visual integrity7.5/105.5/10

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

GPT-6 Astra

A richly composed sunset beach illustration with cohesive peach, mauve and teal colors. Sweeping palm fronds, a scalloped umbrella and curved shorelines frame the sun and its aligned reflection. Distinct animal silhouettes and carefully distributed beach details reward inspection. Simplified human and dog anatomy, slight dolphin splash cues and inconsistent equipment shadows limit physical conviction.

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.

Score breakdown

CategoryGPT-6 AstraMiMo-V2.6-Flash
Task & likeness9.0/107.5/10
Anatomy & construction7.5/106.5/10
Space & placement8.5/107.0/10
Light & reflections7.5/106.0/10
Purposeful detail8.5/107.0/10
Artistry & character8.5/106.0/10
Materials & effects7.5/106.0/10
Visual integrity7.5/108.0/10

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

GPT-6 Astra

This benchmark has not been assessed yet.

MiMo-V2.6-Flash

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

GPT-6 Astra

A controlled, expressive illustration with readable riding and steering, articulated poses and purposeful small details. Layered foam and coherent hull perspective establish motion and depth. Simplified paws, compressed control fittings and limited directional lighting constrain its physical sophistication.

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.

Score breakdown

CategoryGPT-6 AstraMiMo-V2.6-Flash
Task & likeness8.5/106.5/10
Anatomy & construction7.5/104.0/10
Space & placement7.5/106.5/10
Light & reflections6.5/104.5/10
Purposeful detail8.0/105.5/10
Artistry & character7.5/104.0/10
Materials & effects7.5/105.5/10
Visual integrity8.0/106.0/10

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

GPT-6 Astra

The pelican's long bill, flowing scarf and warm coastal palette create a charming, balanced illustration. Wheels, spokes and frame are largely coherent, but neither wing reaches the handlebars, and the rear leg's pedal contact is unclear. Flat lighting and simplified surfaces limit depth despite clean outlines and attractive feather detail.

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.

Score breakdown

CategoryGPT-6 AstraMiMo-V2.6-Flash
Task & likeness8.0/108.0/10
Anatomy & construction7.0/105.5/10
Space & placement7.5/107.0/10
Light & reflections7.0/106.0/10
Purposeful detail8.0/107.0/10
Artistry & character8.0/106.5/10
Materials & effects7.5/105.5/10
Visual integrity8.0/107.5/10

Benchmark task

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