STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6.1 Sol vs MiniMax M3.1 Flash

GPT-6.1 Sol leads MiniMax M3.1 Flash by 21.9 points on StealthMark, 67.8 to 45.9. It leads on all 9 benchmarks. GPT-6.1 Sol scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

67.8/100Overall rank 4/53
45.9/100Overall rank 24/53

General Intelligence

64.4/100
35.8/100

Visual Intelligence

74.1/100
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

  • GPT-6.1 Sol

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6.1 Sol
  • MiniMax M3.1 Flash
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1.05M tokens of context.

  • GPT-6.1 Sol
  • MiniMax M3.1 Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6.1 Sol: $10$2 inputMiniMax M3.1 Flash: No list price
Context windowTokens per request, max output below
GPT-6.1 Sol: 1.05MTied128K max outputMiniMax M3.1 Flash: 1MTied
Output speedTokens per second, our measurement
GPT-6.1 Sol: 51tokens/sMiniMax M3.1 Flash: Not measured
SizeTotal and active parameters
GPT-6.1 Sol: Not disclosedMiniMax M3.1 Flash: 428B23B active
Developer
OpenAIMiniMax
Released
29 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-6.1 Sol ↗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-6.1 Sol 62.0/100Rank 9/47

Survived 2 of 3
Foresight: complete playing field
Level 318 ptsTurn 20 / 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-6.1 SolMiniMax M3.1 Flash
Level 1Second Thoughts
26 ptsSurvived
6 ptsOut of lives
Level 2Pressure Pot
6 ptsOut of lives
5 ptsOut of lives
Level 3Hide or Flight
18 ptsSurvived
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-6.1 Sol 87.6/100Rank 1/48

Cleared 5 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 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-6.1 SolMiniMax M3.1 Flash
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
10.2 ptsClearedFinished early · 1 beacon left
8.6 ptsClearedFinished early · 1 beacon left
Level 3Relay vault
19.2 ptsCleared
5 ptsOut of turns
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
4.4 ptsFinished early
Level 5Second thoughts
20.6 ptsCleared
17.2 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

GPT-6.1 Sol

Recognizable first sphere images and several central planar lights provide limited geometric agreement. Missing outer chains, truncated panel sequences and simplified interiors across the main, side and floor spheres leave most of the recursive reflection structure unsupported.

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-6.1 SolMiniMax M3.1 Flash
State at 600 ms24.0/2520.0/25
Camera and placement15.0/1510.0/15
Reflections35.0/12024.0/120
Materials and scale10.0/108.0/10
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-6.1 Sol

Six outward-facing heads and evenly arranged loops make the pale interlocking knot immediately readable. Uniform widths, angular inner bends and fine scales preserve its ornamental geometry. The bodies feel more like textured tubes than living muscle: shading is subdued, crossing contact shadows are weak, and visible curved seams interrupt surface continuity. Small heads have readable eyes and jaws but limited anatomical depth.

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-6.1 SolMiniMax M3.1 Flash
Task & likeness8.5/107.5/10
Anatomy & construction7.5/106.0/10
Space & placement8.0/107.0/10
Light & reflections7.0/106.0/10
Purposeful detail7.5/105.0/10
Artistry & character7.5/106.0/10
Materials & effects7.0/107.0/10
Visual integrity8.0/106.0/10

Benchmark task

GPT-6.1 Sol

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-6.1 Sol

The recognizable pose, dark clothing and misty landscape form a coherent portrait. Soft facial shading creates volume, but the broad face, outlined eyes and simplified smile limit likeness. Overlapping hands have flattened fingers and ambiguous separation. Angular landscape shapes and sparse fabric detail keep the execution competent rather than masterful.

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-6.1 SolMiniMax M3.1 Flash
Task & likeness6.5/104.0/10
Anatomy & construction5.5/104.5/10
Space & placement6.5/105.5/10
Light & reflections6.5/104.5/10
Purposeful detail5.5/105.5/10
Artistry & character6.5/106.0/10
Materials & effects6.0/105.5/10
Visual integrity7.0/105.5/10

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-6.1 Sol

A cohesive sunset palette, sweeping shoreline and framing palm create an appealing beach illustration. Animals, birds, play and a prominent sun reflection fulfill the brief. Connected but schematic figures and simplified dolphin anatomy limit construction; stepped reflections and mostly flat surfaces limit lighting and material depth. Small beach accessories remain readable and edges are clean.

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-6.1 SolMiniMax M3.1 Flash
Task & likeness8.5/108.5/10
Anatomy & construction7.5/107.0/10
Space & placement7.5/107.5/10
Light & reflections7.5/106.0/10
Purposeful detail7.5/108.0/10
Artistry & character7.0/106.5/10
Materials & effects7.0/106.5/10
Visual integrity8.5/107.5/10

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-6.1 Sol

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-6.1 Sol

The masked raccoon rides the dog's back, and the dog's forepaw meets a handlebar connected to the deck. Expressive faces, a striped tail and sweeping wake create an appealing composition. Overlapping bodies compress the seating and rear-leg anatomy; hull depth and sunset illumination remain schematic.

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-6.1 SolMiniMax M3.1 Flash
Task & likeness8.5/109.0/10
Anatomy & construction7.5/108.0/10
Space & placement7.5/108.0/10
Light & reflections6.5/106.0/10
Purposeful detail8.0/107.5/10
Artistry & character8.0/107.5/10
Materials & effects7.5/107.0/10
Visual integrity8.5/108.0/10

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-6.1 Sol

A clearly recognizable pelican rides a well-composed bicycle through a warm coastal scene. The expressive bill, restrained palette and carefully drawn wheels give the illustration character. Leg-to-pedal connections are less convincing, especially the obscured far foot. Lighting provides gentle volume but little directional shadow. The small subtitle is clipped at the lower border.

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-6.1 SolMiniMax M3.1 Flash
Task & likeness9.0/108.5/10
Anatomy & construction7.0/106.5/10
Space & placement8.0/108.0/10
Light & reflections7.0/107.0/10
Purposeful detail8.0/107.5/10
Artistry & character8.5/106.5/10
Materials & effects7.5/107.0/10
Visual integrity8.0/106.5/10

Benchmark task

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