STEALTHMARK · HEAD TO HEAD

All comparisons ↗

MiniMax M3.1 Flash (early version) vs Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) leads MiniMax M3.1 Flash (early version) by 17.1 points on StealthMark, 62.6 to 45.5. It leads on 6 of 9 benchmarks, including both games, and MiniMax M3.1 Flash (early version) on 3. Union Alpha scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
Model guide ↗
Model guide ↗

Overall StealthMark

45.5/100Overall rank 31/58
62.6/100Overall rank 8/58

General Intelligence

35.7/100
58.7/100

Visual Intelligence

64.4/100
69.6/100

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

  • MiniMax M3.1 Flash (early version)
  • Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)Not measured

Cost efficiency

How much Performance you get for your money.

BENCHMARK BY BENCHMARK

Where each model leads

  • MiniMax M3.1 Flash (early version)
  • Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
  • Other models
  • Median

DATASHEET

Specs and pricing

MiniMax M3.1 Flash (early version) runs 12× faster in our speed test. Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) scores higher on StealthMark.

  • MiniMax M3.1 Flash (early version)
  • Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
  • Other models
  • Median
Context windowTokens per request, max output below
MiniMax M3.1 Flash (early version): Not publishedPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM): 262K131K max output
Output speedTokens per second, our measurement
MiniMax M3.1 Flash (early version): 30012× fastertokens/sPareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM): 26tokens/s
Developer
Not publishedCircuit & Chisel / Unbiased
Released
Not published20 Sep 2026
Origin
Not publishedUnited States
Input → output
Not publishedText, image → text

Full datasheets, every price and sourcePareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) ↗

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.

MiniMax M3.1 Flash (early version) 35.8/100Rank 29/54

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 19 / 20

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 78.7/100Rank 1/54

Survived 2 of 3
Foresight: complete playing field
Level 319 ptsTurn 20 / 20

Points per level

LevelMiniMax M3.1 Flash (early version)Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Level 1Second Thoughts
16 ptsOut of lives
27 ptsSurvived
Level 2Pressure Pot
6 ptsOut of lives
12 ptsOut of lives
Level 3Hide or Flight
8 ptsOut of lives
19 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.

MiniMax M3.1 Flash (early version) 34.4/100Rank 40/55

Cleared 3 of 5
Latch: complete playing field
Level 512.6 ptsTurn 17 / 40

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 36.5/100Rank 37/55

Cleared 4 of 5
Latch: complete playing field
Level 519.4 ptsTurn 33 / 40

Points per level

LevelMiniMax M3.1 Flash (early version)Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Level 1Hold the door
5 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9 ptsCleared
9.8 ptsCleared
Level 3Relay vault
16.2 ptsClearedFinished early · 3 beacons left
14.2 ptsClearedFinished early · 4 beacons left
Level 4Passing bay
10.4 ptsFinished early
9.2 ptsFinished early
Level 5Second thoughts
12.6 ptsFinished early
19.4 ptsCleared

Newton's Mirror

Same task instructions

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

MiniMax M3.1 Flash (early version) 24.9/100 Rank 39/58

Space Bunny Alpha: Newton's Mirror SVG benchmark
29 Sep onwardResult details ↗

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 52.0/100 Rank 8/58

Union Alpha: Newton's Mirror SVG benchmark

The judgment

MiniMax M3.1 Flash (early version)

Visible panel shapes, curved sphere highlights, rounded side images and a lower continuation beneath the large left image establish recognizable local mirror structure. Their uneven arrangement, missing receding chains and absent nested imagery remain substantial shortcomings. The main sphere's framing is close, but black lacks projected separation and cyan does not establish recent apex contact.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

Recognizable near-field sphere placement and bilateral convergence provide limited optical structure. Broad gray regions interrupt lateral sightlines and truncate side-floor images. Missing outer chains, absent nested sphere imagery and incomplete planar and curved emitter mappings dominate the reflection system.

Score breakdown

CategoryMiniMax M3.1 Flash (early version)Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
State at 600 ms11.0/2524.0/25
Camera and placement9.0/1513.5/15
Reflections15.5/12034.5/120
Materials and scale7.5/1010.0/10
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.

MiniMax M3.1 Flash (early version) 78.9/100 Rank 3/58

Space Bunny Alpha: Selfie SVG benchmark
29 Sep onwardResult details ↗

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 76.5/100 Rank 6/58

Union Alpha: Selfie SVG benchmark

The judgment

MiniMax M3.1 Flash (early version)

The expressive rabbits, lavender moon and diagonal ring create an appealing storybook composition with nearly all requested features. Glossy eyes and pearly highlights work well. The helmet leaves the towering ears unenclosed, the reaching arm has little joint definition, and the spread boots suggest hovering more clearly than pushing off. Repeated scalloped fur marks and broad gradients limit material depth; purple edge halos soften otherwise controlled silhouettes.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

A strong futuristic emblem with clear hierarchy, controlled negative space and distinctive typography. Silver and gunmetal layers give the sweeping ribbons convincing graphic depth, while red accents remain restrained. Ambiguous concealed connections and occasionally abrupt highlight bands limit the construction and material realism.

Score breakdown

CategoryMiniMax M3.1 Flash (early version)Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness8.5/109.0/10
Anatomy & construction7.5/107.5/10
Space & placement7.5/108.5/10
Light & reflections8.0/107.5/10
Purposeful detail8.0/107.0/10
Artistry & character8.0/107.5/10
Materials & effects7.5/107.5/10
Visual integrity8.0/107.0/10

Benchmark task

MiniMax M3.1 Flash (early version)

An astronaut rabbit reaches for a carrot above a small moon while a younger companion peeks into view. The scene tests expressive characters, spatial relationships and material detail.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

An interwoven metallic emblem tests ribbon geometry, overlapping forms and the appearance of reflective metal against a dark background.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

MiniMax M3.1 Flash (early version) 49.9/100 Rank 19/58

Space Bunny Alpha: Mona Lisa SVG benchmark
29 Sep onwardResult details ↗

The judgment

MiniMax M3.1 Flash (early version)

The dark clothing, folded hands and muted landscape make the reference recognizable. Replication is limited by the broad frontal face, oversized head, explicit smile and simplified landscape. Arms connect coherently, but overlapping hands lack convincing finger construction. Soft gradients suggest volume and atmospheric depth; clothing folds and facial features remain schematic.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

The centered portrait, folded hands, dark clothing and hazy landscape clearly evoke the Mona Lisa. Muted colors and soft facial shading create a coherent illustration, but replication remains schematic: the face is broad, eyes outlined, smile simplified and overlapping fingers poorly resolved. Angular landscape shapes and flat fabric limit depth and painterly richness.

Score breakdown

CategoryMiniMax M3.1 Flash (early version)Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness4.5/106.5/10
Anatomy & construction5.0/105.0/10
Space & placement5.5/106.5/10
Light & reflections6.0/106.0/10
Purposeful detail4.0/105.5/10
Artistry & character5.0/106.5/10
Materials & effects4.5/105.0/10
Visual integrity5.5/107.0/10

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.

MiniMax M3.1 Flash (early version) 67.8/100 Rank 21/58

Space Bunny Alpha: Beach SVG benchmark
29 Sep onwardResult details ↗

The judgment

MiniMax M3.1 Flash (early version)

A cheerful, coherent beach illustration with a strong sunset focal point, varied animals and readable small accessories. Connected flamingo legs and grounded foreground objects support the scene. Construction remains schematic, especially the airborne marine animal; its jump lacks clear water displacement. The sun reflection is effective but geometrically rigid, while shadows and material textures provide limited depth.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

A cohesive sunset palette, sweeping shoreline and playful animals make an appealing beach illustration. The sun’s reflection establishes a clear focal axis, balanced by the palm and umbrella. Clean silhouettes and small decorative features reward inspection, though simplified anatomy, repetitive reflection bars and generic oval shadows limit volume and naturalism.

Score breakdown

CategoryMiniMax M3.1 Flash (early version)Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness8.5/109.0/10
Anatomy & construction6.0/107.0/10
Space & placement6.0/108.0/10
Light & reflections7.0/107.0/10
Purposeful detail6.5/107.0/10
Artistry & character6.5/106.0/10
Materials & effects6.0/106.5/10
Visual integrity7.5/107.0/10

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.

MiniMax M3.1 Flash (early version) 42.7/100 Rank 25/58

Space Bunny Alpha: Ground Truth SVG benchmark
29 Sep onwardResult details ↗

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM) 63.3/100 Rank 9/58

Union Alpha: Ground Truth SVG benchmark

The judgment

MiniMax M3.1 Flash (early version)

This benchmark has not been assessed yet.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

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

MiniMax M3.1 Flash (early version)

The raccoon clearly rides on the dog's back, and the dog's paws reach a connected steering assembly. Expressive faces, controlled outlines and layered mountains make an appealing illustration. The seated anatomy and hull geometry are simplified, while the sunset has little corresponding reflection or directional shading. Curved spray conveys motion, although several splash ribbons look decorative.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

Expressive animals, a readable riding arrangement and sweeping spray create an appealing cartoon. The raccoon sits convincingly on the dog's back, but the dog's paw does not clearly grip the handlebar, whose connection to the hull is unresolved. Flat lighting provides little volume or reflection. A dark rectangular strip interrupts the upper-right background.

Score breakdown

CategoryMiniMax M3.1 Flash (early version)Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness8.0/108.0/10
Anatomy & construction7.5/106.5/10
Space & placement7.5/107.5/10
Light & reflections6.5/105.5/10
Purposeful detail7.5/107.0/10
Artistry & character7.0/107.0/10
Materials & effects7.0/107.5/10
Visual integrity8.5/107.0/10

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.

MiniMax M3.1 Flash (early version) 68.0/100 Rank 23/58

Space Bunny Alpha: Pelican SVG benchmark
29 Sep onwardResult details ↗

The judgment

MiniMax M3.1 Flash (early version)

The large pouched bill clearly identifies the pelican, and the balanced bicycle silhouette makes the action readable. Attached legs reach the crank area, but overlapping feet and crank lines leave pedal contact ambiguous. Consistent wheel scale, clean contours and a restrained coastal palette support an appealing composition. Lighting and surface treatment remain simple and mostly flat.

Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)

The pelican is immediately recognizable, with an expressive face, convincing bill silhouette and appealing pastel composition. Both legs connect to feet, and the wing reaches the handlebar. Bicycle construction is less resolved: the far pedal lacks a clear crank connection and no chain is visible. Clean contours and orderly spokes support the illustration, while flat lighting and simplified surfaces limit depth.

Score breakdown

CategoryMiniMax M3.1 Flash (early version)Pareto 26.9 (Union of GPT-6 Astra + DeepSeek + GLM)
Task & likeness7.5/108.0/10
Anatomy & construction6.5/106.0/10
Space & placement7.5/107.0/10
Light & reflections6.5/106.0/10
Purposeful detail7.0/106.0/10
Artistry & character5.5/106.0/10
Materials & effects6.5/106.0/10
Visual integrity7.5/108.5/10

Benchmark task

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