STEALTHMARK · HEAD TO HEAD

All comparisons ↗

DeepSeek-V4-Pro-0813 vs MiniMax M3.1 Flash (early version)

MiniMax M3.1 Flash (early version) leads DeepSeek-V4-Pro-0813 by 2.7 points on StealthMark, 45.5 to 42.8. It leads on 6 of 9 benchmarks and DeepSeek-V4-Pro-0813 on 3, including both games. DeepSeek-V4-Pro-0813 scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

42.8/100Overall rank 36/58
45.5/100Overall rank 31/58

General Intelligence

41.9/100
35.7/100

Visual Intelligence

44.6/100
64.4/100

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)

Cost efficiency

How much Performance you get for your money.

Open or local

Open modelMIT

BENCHMARK BY BENCHMARK

Where each model leads

  • DeepSeek-V4-Pro-0813
  • MiniMax M3.1 Flash (early version)
  • Other models
  • Median

DATASHEET

Specs and pricing

MiniMax M3.1 Flash (early version) scores higher on StealthMark and runs 2.2× faster in our speed test.

  • DeepSeek-V4-Pro-0813
  • MiniMax M3.1 Flash (early version)
  • Other models
  • Median
PricePer 1M output tokens, input below
DeepSeek-V4-Pro-0813: $3.82$1.27 inputMiniMax M3.1 Flash (early version): No list price
Context windowTokens per request, max output below
DeepSeek-V4-Pro-0813: 1M384K max outputMiniMax M3.1 Flash (early version): Not published
Output speedTokens per second, our measurement
DeepSeek-V4-Pro-0813: 137tokens/sMiniMax M3.1 Flash (early version): 3002.2× fastertokens/s
SizeTotal and active parameters
DeepSeek-V4-Pro-0813: 1.6T49B activeMiniMax M3.1 Flash (early version): Not disclosed
Developer
DeepSeek-AINot published
Released
13 Aug 2026Not published
Origin
ChinaNot published
Input → output
Text → textNot published
Architecture
Mixture-of-Experts with DeepSeek V4 architecture and DSpark speculative-decoding moduleNot published

Full datasheets, every price and sourceDeepSeek-V4-Pro-0813 ↗

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.

DeepSeek-V4-Pro-0813 42.7/100Rank 26/54

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

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

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

Points per level

LevelDeepSeek-V4-Pro-0813MiniMax M3.1 Flash (early version)
Level 1Second Thoughts
14 ptsOut of lives
16 ptsOut of lives
Level 2Pressure Pot
6 ptsOut of lives
6 ptsOut of lives
Level 3Hide or Flight
9 ptsSurvived
8 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.

DeepSeek-V4-Pro-0813 71.7/100Rank 18/55

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

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

Points per level

LevelDeepSeek-V4-Pro-0813MiniMax M3.1 Flash (early version)
Level 1Hold the door
5.2 ptsCleared
5 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
9 ptsCleared
Level 3Relay vault
18.8 ptsCleared
16.2 ptsClearedFinished early · 3 beacons left
Level 4Passing bay
17.2 ptsClearedFinished early · 1 beacon left
10.4 ptsFinished early
Level 5Second thoughts
20.6 ptsCleared
12.6 ptsFinished early

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 ↗

The judgment

DeepSeek-V4-Pro-0813

The central sphere and gross paint state are coherent. Reduced circular side images and paired overhead quadrilaterals offer limited, spatially organized reflection cues, but the floor-sphere image, receding mirror-room structure, outer chains, nested imagery and curved emitter mappings are largely missing or invalid.

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.

Score breakdown

CategoryDeepSeek-V4-Pro-0813MiniMax M3.1 Flash (early version)
State at 600 ms22.0/2511.0/25
Camera and placement15.0/159.0/15
Reflections11.0/12015.5/120
Materials and scale8.0/107.5/10
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.

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

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

The judgment

DeepSeek-V4-Pro-0813

The whale’s warm eye, lavender assistant and tilted shell convey appealing character. However, the shrimp and reciprocal inspection are unresolved, the large bubble and upper tail are cropped, and the flipper’s grip is unclear. Broad competing color fields and conspicuous stepped edges weaken the flowing composition. Gradients suggest volume, but lighting and translucent materials remain uneven.

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.

Score breakdown

CategoryDeepSeek-V4-Pro-0813MiniMax M3.1 Flash (early version)
Task & likeness3.0/108.5/10
Anatomy & construction5.0/107.5/10
Space & placement4.0/107.5/10
Light & reflections5.5/108.0/10
Purposeful detail5.5/108.0/10
Artistry & character2.5/108.0/10
Materials & effects5.0/107.5/10
Visual integrity3.0/108.0/10

Benchmark task

DeepSeek-V4-Pro-0813

A whale and a tiny shrimp examine one another through bubble lenses, with an octopus nearby. The scene tests interacting characters, differences in scale and transparent materials.

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.

Mona Lisa

Different 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

DeepSeek-V4-Pro-0813

Dark hair, a restrained smile and a hazy landscape make the reference recognizable. Severe construction problems dominate: oversized looping sleeves surround a background-colored opening, and the crossed hands lack coherent wrist and forearm connections. Rigid symmetry and elongated facial proportions weaken expression. Soft skin gradients and clean contours provide limited finish.

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.

Score breakdown

CategoryDeepSeek-V4-Pro-0813MiniMax M3.1 Flash (early version)
Task & likeness2.0/104.5/10
Anatomy & construction0.5/105.0/10
Space & placement2.0/105.5/10
Light & reflections2.0/106.0/10
Purposeful detail2.0/104.0/10
Artistry & character3.0/105.0/10
Materials & effects1.5/104.5/10
Visual integrity1.0/105.5/10

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.

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

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

The judgment

DeepSeek-V4-Pro-0813

A coherent beach illustration with effective sunset lighting, layered depth and playful detail. Organic framing and water effects add control beyond its simple geometry. Flattened architecture, schematic animals, limited materials and the unsupported kite constrain the finish.

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.

Score breakdown

CategoryDeepSeek-V4-Pro-0813MiniMax M3.1 Flash (early version)
Task & likeness8.0/108.5/10
Anatomy & construction5.0/106.0/10
Space & placement6.0/106.0/10
Light & reflections7.0/107.0/10
Purposeful detail6.0/106.5/10
Artistry & character5.5/106.5/10
Materials & effects6.5/106.0/10
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.

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

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

The judgment

DeepSeek-V4-Pro-0813

This benchmark has not been assessed yet.

MiniMax M3.1 Flash (early version)

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

DeepSeek-V4-Pro-0813

The masked raccoon riding the steering dog is readily recognizable, with expressive faces and energetic diagonal movement. The oversized tail dominates the composition, limb connections are difficult to trace, and the jet ski has little structural depth. Blurred spray and a heavy oval shadow weaken water contact, while the glowing sun produces little corresponding illumination.

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.

Score breakdown

CategoryDeepSeek-V4-Pro-0813MiniMax M3.1 Flash (early version)
Task & likeness7.0/108.0/10
Anatomy & construction4.5/107.5/10
Space & placement6.0/107.5/10
Light & reflections4.5/106.5/10
Purposeful detail6.0/107.5/10
Artistry & character4.5/107.0/10
Materials & effects5.0/107.0/10
Visual integrity4.0/108.5/10

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

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

DeepSeek-V4-Pro-0813

A clearly recognizable pelican cycles through a balanced, expressive illustration. The sweeping bill, shaded plumage and carefully drawn wheels give it character. Mechanical construction is weaker: the chain loop sits below the crank, and foot-to-pedal and wing-to-handlebar contact are ambiguous. Smooth gradients provide volume, but the scene remains visibly stylized.

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.

Score breakdown

CategoryDeepSeek-V4-Pro-0813MiniMax M3.1 Flash (early version)
Task & likeness8.0/107.5/10
Anatomy & construction5.0/106.5/10
Space & placement6.5/107.5/10
Light & reflections7.0/106.5/10
Purposeful detail7.0/107.0/10
Artistry & character5.5/105.5/10
Materials & effects7.0/106.5/10
Visual integrity5.0/107.5/10

Benchmark task

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