STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6 Luna vs MiniMax M3.1 Flash

MiniMax M3.1 Flash leads GPT-6 Luna by 6.8 points on StealthMark, 45.9 to 39.1. It leads on 8 of 9 benchmarks, including Foresight, and GPT-6 Luna on 1, including Latch. MiniMax M3.1 Flash scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

39.1/100Overall rank 35/53
45.9/100Overall rank 24/53

General Intelligence

31.3/100
35.8/100

Visual Intelligence

52.0/100
62.6/100

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

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6 Luna
  • MiniMax M3.1 Flash
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1.05M tokens of context.

  • GPT-6 Luna
  • MiniMax M3.1 Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6 Luna: $0.50$0.10 inputMiniMax M3.1 Flash: No list price
Context windowTokens per request, max output below
GPT-6 Luna: 1.05MTied128K max outputMiniMax M3.1 Flash: 1MTied
Output speedTokens per second, our measurement
GPT-6 Luna: 131tokens/sMiniMax M3.1 Flash: Not measured
SizeTotal and active parameters
GPT-6 Luna: Not disclosedMiniMax M3.1 Flash: 428B23B active
Developer
OpenAIMiniMax
Released
22 Sep 2026Not published
Origin
United StatesNot published
Input → output
Text, image → textText, image, video → text
Architecture
Not publishedMixture-of-Experts with MiniMax Sparse Attention and native multimodal encoder

Full datasheets, every price and sourceGPT-6 Luna ↗MiniMax M3.1 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 Luna 29.8/100Rank 32/47

Survived 0 of 3
Foresight: complete playing field
Level 36 ptsTurn 7 / 20

MiniMax M3.1 Flash 30.7/100Rank 28/47

Survived 1 of 3
Foresight: complete playing field
Level 39 ptsTurn 20 / 20

Points per level

LevelGPT-6 LunaMiniMax M3.1 Flash
Level 1Second Thoughts
15 ptsOut of lives
6 ptsOut of lives
Level 2Pressure Pot
5 ptsOut of lives
5 ptsOut of lives
Level 3Hide or Flight
6 ptsOut of lives
9 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.

GPT-6 Luna 44.0/100Rank 25/48

Cleared 4 of 5
Latch: complete playing field
Level 513 ptsTurn 15 / 40

MiniMax M3.1 Flash 21.9/100Rank 38/48

Cleared 2 of 5
Latch: complete playing field
Level 517.2 ptsTurn 24 / 40

Points per level

LevelGPT-6 LunaMiniMax M3.1 Flash
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
8.8 ptsClearedFinished early · 1 beacon left
8.6 ptsClearedFinished early · 1 beacon left
Level 3Relay vault
17 ptsCleared1 beacon left
5 ptsOut of turns
Level 4Passing bay
15.8 ptsClearedFinished early · 3 beacons left
4.4 ptsFinished early
Level 5Second thoughts
13 ptsFinished early
17.2 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

GPT-6 Luna

The schematic scene supports the paint contact order and compact paint scale. Its low, undersized main sphere and incorrectly placed wall images depart from the reference geometry. A few shrinking wall images provide limited optical organization, while absent lateral recursion and outer chains, broad sphere ribbons and isolated panel highlights leave most nested room and emitter mapping undeveloped.

MiniMax M3.1 Flash

The sphere placement, separate airborne black blob, recent cyan contact and elongated crimson aftermath support the required gross physical state. The reflection system remains severely incomplete: isolated side images, broad metallic bands and sparse light patches replace extensive mirror repetitions and curved nested imagery.

Score breakdown

CategoryGPT-6 LunaMiniMax M3.1 Flash
State at 600 ms22.0/2520.0/25
Camera and placement3.5/1510.0/15
Reflections5.0/12024.0/120
Materials and scale7.0/108.0/10
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

GPT-6 Luna

Sixfold symmetry, pale coloring and six outward-facing heads establish the motif. However, every neck floats clear of the knot. Squared outer sections replace the required semicircular lobes, and the large stepped opening lacks a regular hexagonal contour. Repeated scales and soft shading suggest skin, but translucent crossings and doubled edges weaken the living, interwoven construction.

MiniMax M3.1 Flash

The sculptural M, confident grin and miniature theatrical pose closely fulfill the brief. Controlled gradients and clean shapes give the character volume and appeal. Moderate drawing complexity, an apparently separated shoe and ambiguous grounding limit the finish.

Score breakdown

CategoryGPT-6 LunaMiniMax M3.1 Flash
Task & likeness4.5/107.5/10
Anatomy & construction3.5/106.0/10
Space & placement5.5/107.0/10
Light & reflections5.0/106.0/10
Purposeful detail5.0/105.0/10
Artistry & character5.0/106.0/10
Materials & effects5.0/107.0/10
Visual integrity4.5/106.0/10

Benchmark task

GPT-6 Luna

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.

MiniMax M3.1 Flash

A small robot with an oversized angular head presents a glowing object. The scene tests character proportions, gesture and contrasting materials.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

GPT-6 Luna

The dark veil, crossed arms, restrained smile and layered landscape clearly evoke Mona Lisa. Clean contours and muted colors create a coherent illustration. Replication is limited by enlarged, outlined eyes, simplified facial volume, broad shoulders and indistinct overlapping hands. Gradients suggest depth, but lack the original's subtle painterly transitions.

MiniMax M3.1 Flash

A coherent decorative portrait combines layered hair, garment contours, linked trim and atmospheric scenery. These provide meaningful drawing complexity, but likeness remains limited by the frontal elongated face and altered clothing. Compressed hands, abrupt facial shading and cluttered local edges leave the portrait uneven.

Score breakdown

CategoryGPT-6 LunaMiniMax M3.1 Flash
Task & likeness4.5/104.0/10
Anatomy & construction4.0/104.5/10
Space & placement5.5/105.5/10
Light & reflections5.0/104.5/10
Purposeful detail5.0/105.5/10
Artistry & character4.5/106.0/10
Materials & effects5.0/105.5/10
Visual integrity6.0/105.5/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Different task instructions

Creativity, perspective and visual beauty.

The judgment

GPT-6 Luna

The warm sky, layered sea and framing palms create an appealing beach composition. Animals, birds, toys and reflected sunlight fulfill the brief. Human anatomy remains schematic, and simplified figures offer limited expression. Missing shadows and the dolphin's splashless jump weaken physical grounding, while clean silhouettes and readable small details support the illustration.

MiniMax M3.1 Flash

A controlled, detailed beach illustration with expressive animals, coherent depth and accomplished foliage and accessory drawing. Its warm palette and varied contours sustain visual interest. Simplified anatomy and object volumes limit physical conviction, while reflection streaks crossing dry-looking sand and generic shadows weaken the lighting.

Score breakdown

CategoryGPT-6 LunaMiniMax M3.1 Flash
Task & likeness7.5/108.5/10
Anatomy & construction5.0/107.0/10
Space & placement7.5/107.5/10
Light & reflections5.0/106.0/10
Purposeful detail7.0/108.0/10
Artistry & character5.0/106.5/10
Materials & effects6.5/106.5/10
Visual integrity6.0/107.5/10

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

GPT-6 Luna

This benchmark has not been assessed yet.

MiniMax M3.1 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

Different task instructions

Scene composition and interacting subjects.

The judgment

GPT-6 Luna

Expressive faces, warm sunset colors and clean silhouettes create an appealing illustration. The raccoon sits on the dog's back, but the dog's grip and steering linkage remain unclear. The broad hull resembles a speedboat, and flat shading, absent sun reflections and modest water displacement limit depth and motion.

MiniMax M3.1 Flash

An expressive, coherent cartoon clearly demonstrates the requested riding and steering relationship. Layered animal shapes, readable vehicle depth and purposeful facial details support its drawing quality. Ambiguous grips, sparse cast shadows and simplified material responses limit physical precision.

Score breakdown

CategoryGPT-6 LunaMiniMax M3.1 Flash
Task & likeness8.0/109.0/10
Anatomy & construction5.5/108.0/10
Space & placement7.5/108.0/10
Light & reflections6.0/106.0/10
Purposeful detail7.0/107.5/10
Artistry & character5.5/107.5/10
Materials & effects6.5/107.0/10
Visual integrity5.0/108.0/10

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

Different task instructions

Subject construction and spatial relationships.

The judgment

GPT-6 Luna

The pelican’s distinctive bill and the coordinated vintage poster palette make an appealing illustration. Circular wheels, orderly spokes and clean lettering strengthen the design. Riding mechanics are less convincing: neither wing reaches the handlebars, pedal contact is ambiguous, and the drivetrain is incomplete. The wheels sit against water without a clear supporting surface. Flat lighting limits volume.

MiniMax M3.1 Flash

A controlled coastal illustration with a clear pelican silhouette, detailed wheels and accomplished feather and bill drawing. Continuous body construction and grounded wheels support the scene. Ambiguous leg, pedal and steering contacts weaken the riding mechanics; approximate directional lighting and simplified materials limit physical conviction.

Score breakdown

CategoryGPT-6 LunaMiniMax M3.1 Flash
Task & likeness8.0/108.5/10
Anatomy & construction5.0/106.5/10
Space & placement6.5/108.0/10
Light & reflections6.5/107.0/10
Purposeful detail7.5/107.5/10
Artistry & character6.5/106.5/10
Materials & effects6.5/107.0/10
Visual integrity7.0/106.5/10

Benchmark task

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