STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Mistral Large 4 vs Step 5 Preview

Mistral Large 4 leads Step 5 Preview by 4.3 points on StealthMark, 43.3 to 39.0. It leads on 8 of 9 benchmarks, including both games, and Step 5 Preview on 1. Step 5 Preview scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

43.3/100Overall rank 31/53
39.0/100Overall rank 36/53

General Intelligence

34.4/100
37.1/100

Visual Intelligence

58.0/100
41.9/100

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

  • Mistral Large 4
  • Step 5 Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1M tokens of context.

  • Mistral Large 4
  • Step 5 Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
Mistral Large 4: $4.18$1.36 inputStep 5 Preview: No list price
Context windowTokens per request, max output below
Mistral Large 4: 1MTied256K max outputStep 5 Preview: 1MTied
Output speedTokens per second, our measurement
Mistral Large 4: 151tokens/sStep 5 Preview: Not measured
SizeTotal and active parameters
Mistral Large 4: 1.05T49B activeStep 5 Preview: 600B27B active
Developer
Mistral AIStepFun
Released
6 Oct 2026Not published
Origin
FranceNot published
Input → output
Text, image → textText, image, video → text
Architecture
Granular mixture of experts (MoE); multimodal text and image input, text output.Sparse mixture-of-experts; 92 layers (88 MoE), 352 routed experts with 8 selected per token plus a shared expert; grouped-query attention with 512-token sliding windows and full attention every fourth layer; 3 multi-token-prediction layers; vision tower for image and video input

Full datasheets, every price and sourceMistral Large 4 ↗Step 5 Preview ↗

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.

Mistral Large 4 22.0/100Rank 40/49

Survived 0 of 3
Foresight: complete playing field
Level 34 ptsTurn 8 / 20

Step 5 Preview 59.9/100Rank 42/491 of 3 levels

1 of 3 played
Foresight: complete playing field
Level 122 ptsTurn 28 / 28

Points per level

LevelMistral Large 4Step 5 Preview
Level 1Second Thoughts
1 ptsOut of lives
22 ptsSurvived
Level 2Pressure Pot
9 ptsOut of lives
Pending
Level 3Hide or Flight
4 ptsOut of lives
Pending

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.

Mistral Large 4 49.4/100Rank 25/50

Cleared 5 of 5
Latch: complete playing field
Level 519.8 ptsTurn 31 / 40

Step 5 Preview 40.7/100Rank 28/50

Cleared 4 of 5
Latch: complete playing field
Level 515 ptsTurn 35 / 40

Points per level

LevelMistral Large 4Step 5 Preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
9 ptsCleared
Level 3Relay vault
15.8 ptsClearedFinished early · 3 beacons left
18.6 ptsCleared
Level 4Passing bay
16.2 ptsClearedFinished early · 3 beacons left
15.6 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
19.8 ptsCleared
15 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

Mistral Large 4

The central sphere, airborne black and deformed crimson support substantial state and placement credit. Recent cyan contact and crimson transport remain uncertain. Sparse wall patches and glossy gradients provide little evidence of the required extensive mirror system, while the missing centerline lamp and bulky crimson remain visible weaknesses.

Step 5 Preview

The main sphere, airborne black and small colored features occupy broadly appropriate positions. Most of the defining mirror system is absent, and paint interaction remains only partially supported. The small paint features do not visibly establish a separate volume-scale violation.

Score breakdown

CategoryMistral Large 4Step 5 Preview
State at 600 ms17.0/2520.0/25
Camera and placement11.0/1513.5/15
Reflections12.0/12020.0/120
Materials and scale5.5/107.0/10
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

Mistral Large 4

An appealing, coherent illustration whose enormous rounded cat anchors the windblown composition. Warm shading and floating sketches communicate the brief well. Simplified paws, faint ear construction, inconsistent wind cues and limited material texture keep the execution below exceptional.

Step 5 Preview

A charming diagonal climber and warm palette communicate the central idea. Simple rounded construction, crowded limb counting, uncertain footholds and an unattached upper shelf limit its physical coherence. Growth bands and the yarn trail add specificity, but the requested material distinctions and unravelled bootie remain underdeveloped.

Score breakdown

CategoryMistral Large 4Step 5 Preview
Task & likeness8.0/106.0/10
Anatomy & construction7.0/104.5/10
Space & placement7.5/105.0/10
Light & reflections7.0/105.5/10
Purposeful detail7.0/105.5/10
Artistry & character7.0/105.0/10
Materials & effects7.0/106.0/10
Visual integrity8.0/105.0/10

Benchmark task

Mistral Large 4

A heavy ginger cat stays planted on a terrace as wind carries papers around it. The scene tests weight, expression and the contrast between stable and moving forms.

Step 5 Preview

Character scenes test expression, anatomy, materials and coherent visual construction.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Mistral Large 4

A recognizable, cleanly rendered interpretation with a restrained palette and some facial modeling. Its enlarged frontal head, simplified expression, compressed low hands and schematic landscape substantially limit likeness and construction. The smooth rendering does not reproduce the painting's nuanced anatomy, clothing or atmospheric depth.

Step 5 Preview

A recognizable, coherent simplification with purposeful facial contours and differentiated fingers. These provide more construction and detail than the broad silhouette alone suggests. The oversized face, frontal seated pose, unresolved wrists and sparse landscape still substantially limit likeness, depth and finish.

Score breakdown

CategoryMistral Large 4Step 5 Preview
Task & likeness4.0/104.0/10
Anatomy & construction3.5/104.0/10
Space & placement5.0/104.0/10
Light & reflections4.5/103.5/10
Purposeful detail4.0/104.0/10
Artistry & character4.0/104.0/10
Materials & effects4.5/103.0/10
Visual integrity5.5/103.5/10

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

Mistral Large 4

A clean, appealing beach illustration with clear subject coverage, a cohesive sunset palette and expressive animal details. Bodies and accessories resolve basic construction coherently, although joints remain schematic. Layered shapes establish modest depth; generic oval shadows and flat surfaces limit physical richness. Repeated forms and sparse articulation leave room for more accomplished drawing.

Step 5 Preview

A recognizable sunset beach with clear warm-cool contrast and playful accessories. Basic animal construction, shallow foreground placement and schematic reflections limit spatial and physical credibility. Sparse descriptive detail and abruptly ended sky bands constrain the finish.

Score breakdown

CategoryMistral Large 4Step 5 Preview
Task & likeness7.5/104.0/10
Anatomy & construction6.0/103.0/10
Space & placement7.0/103.5/10
Light & reflections6.5/103.5/10
Purposeful detail6.0/103.0/10
Artistry & character6.0/103.0/10
Materials & effects6.5/103.5/10
Visual integrity8.0/104.0/10

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

Mistral Large 4

This benchmark has not been assessed yet.

Step 5 Preview

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

Mistral Large 4

The central interaction is clear, with recognizable animals, expressive faces and a coherent sunset composition. Clean contours and readable accessories give the cartoon polish. Simplified joints, uncertain steering attachment, shallow hull volume and limited directional lighting constrain its physical resolution.

Step 5 Preview

Recognizable animals, a bright palette and identifying accessories support a basic cartoon. Primitive anatomy, partial seated support, unresolved steering and weak hull-water contact limit the central action. Lighting and spray provide atmosphere without establishing convincing physical depth.

Score breakdown

CategoryMistral Large 4Step 5 Preview
Task & likeness8.5/104.0/10
Anatomy & construction6.5/104.5/10
Space & placement7.0/103.0/10
Light & reflections5.5/103.5/10
Purposeful detail7.5/104.0/10
Artistry & character6.5/103.5/10
Materials & effects6.5/103.0/10
Visual integrity8.0/103.0/10

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

Mistral Large 4

A coherent, appealing pelican illustration with a continuous body silhouette, readable bicycle and grounded wheels. Simplified legs and ambiguous steering and pedal connections limit construction. Clean shapes and expressive accessories succeed, while shallow depth, modest lighting and sparse material differentiation leave substantial room for refinement.

Step 5 Preview

The pelican and bicycle are recognizable, with a pleasant palette and basic diffuse shading. The riding relationship fails physically: the bird is unsupported, the front wheel is unmounted, and pedalling is unresolved. Simple geometric construction and sparse material treatment further limit the drawing.

Score breakdown

CategoryMistral Large 4Step 5 Preview
Task & likeness8.5/103.0/10
Anatomy & construction6.0/103.0/10
Space & placement7.0/103.0/10
Light & reflections6.5/103.0/10
Purposeful detail7.0/104.0/10
Artistry & character7.0/103.0/10
Materials & effects6.5/103.0/10
Visual integrity8.0/102.0/10

Benchmark task

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