STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Nemotron 3 Ultra vs Step 5 Preview

Step 5 Preview leads Nemotron 3 Ultra by 22.3 points on StealthMark, 39.0 to 16.7. It leads on 7 of 9 benchmarks, including both games, and Nemotron 3 Ultra on 2. Step 5 Preview scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

16.7/100Overall rank 49/53
39.0/100Overall rank 36/53

General Intelligence

12.2/100
37.1/100

Visual Intelligence

26.5/100
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

  • Nemotron 3 Ultra
  • Step 5 Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1M tokens of context.

  • Nemotron 3 Ultra
  • Step 5 Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
Nemotron 3 Ultra: $2.40$0.60 inputStep 5 Preview: No list price
Context windowTokens per request, max output below
Nemotron 3 Ultra: 1MTiedStep 5 Preview: 1MTied
Output speedTokens per second, our measurement
Nemotron 3 Ultra: 139tokens/sStep 5 Preview: Not measured
SizeTotal and active parameters
Nemotron 3 Ultra: 550B55B activeStep 5 Preview: 600B27B active
Developer
NVIDIAStepFun
Released
4 Jun 2026Not published
Origin
United StatesNot published
Input → output
Text → textText, image, video → text
Architecture
LatentMoE: Mamba-2 + MoE + Attention hybrid with Multi-Token PredictionSparse 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 sourceNemotron 3 Ultra ↗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.

Nemotron 3 Ultra 16.9/100Rank 43/49

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 17 / 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

LevelNemotron 3 UltraStep 5 Preview
Level 1Second Thoughts
4 ptsOut of lives
22 ptsSurvived
Level 2Pressure Pot
4 ptsOut of lives
Pending
Level 3Hide or Flight
8 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.

Nemotron 3 Ultra 5.0/100Rank 44/504 of 5 levels

4 of 5 played
Latch: complete playing field
Level 413.8 ptsTurn 21 / 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

LevelNemotron 3 UltraStep 5 Preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
3.2 ptsFinished early
9 ptsCleared
Level 3Relay vault
7.4 ptsFinished early
18.6 ptsCleared
Level 4Passing bay
13.8 ptsFinished early
15.6 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
Not played
15 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

Nemotron 3 Ultra

The candidate establishes a separate airborne black blob and partial crimson overlap, but leaves the paint interaction history and settled support unresolved. Its main silhouette, black placement and lamp projection depart substantially from the required camera geometry. A few faint reflection hints provide little support for the extensive mirror system, while the compact paint volumes are visibly disproportionate.

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

CategoryNemotron 3 UltraStep 5 Preview
State at 600 ms2.0/2520.0/25
Camera and placement3.5/1513.5/15
Reflections4.5/12020.0/120
Materials and scale3.0/107.0/10
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

Nemotron 3 Ultra

An endearing mechanical creature is clearly framed, with expressive amber eyes and readable segmented arms. The shell resembles layered green plates more than a deep coiled spiral. Detached-looking construction, absent working contacts and patchy rendering leave the central assembly action substantially unresolved.

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

CategoryNemotron 3 UltraStep 5 Preview
Task & likeness4.0/106.0/10
Anatomy & construction4.0/104.5/10
Space & placement5.5/105.0/10
Light & reflections5.0/105.5/10
Purposeful detail4.0/105.5/10
Artistry & character3.0/105.0/10
Materials & effects4.0/106.0/10
Visual integrity4.5/105.0/10

Benchmark task

Nemotron 3 Ultra

A hovering mechanical nautilus tests spiral construction, connected mechanical forms and contrasting metal and illuminated surfaces.

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

Nemotron 3 Ultra

The centered silhouette provides basic organization, but multicolored mottling and geometric overlays leave the portrait unresolved. No readable face, crossed hands, clothing or landscape establishes Mona Lisa replication. Texture and transparency offer limited visual effects without coherent anatomy, lighting or material distinctions.

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

CategoryNemotron 3 UltraStep 5 Preview
Task & likeness0.5/104.0/10
Anatomy & construction0.0/104.0/10
Space & placement1.0/104.0/10
Light & reflections0.5/103.5/10
Purposeful detail0.5/104.0/10
Artistry & character1.5/104.0/10
Materials & effects0.0/103.0/10
Visual integrity0.5/103.5/10

Benchmark task

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

Beach

Same task instructions

Creativity, perspective and visual beauty.

The judgment

Nemotron 3 Ultra

A recognizable beach illustration with appealing warm-cool contrast, readable layers and mostly clean shapes. Unresolved seat construction, schematic animals and broad geometric foliage give it an elementary finish. Weakly coordinated reflections and limited material differentiation further constrain depth and atmosphere.

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

CategoryNemotron 3 UltraStep 5 Preview
Task & likeness6.5/104.0/10
Anatomy & construction3.0/103.0/10
Space & placement5.0/103.5/10
Light & reflections1.5/103.5/10
Purposeful detail4.5/103.0/10
Artistry & character3.0/103.0/10
Materials & effects2.5/103.5/10
Visual integrity6.5/104.0/10

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

Nemotron 3 Ultra

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

Same task instructions

Scene composition and interacting subjects.

The judgment

Nemotron 3 Ultra

The masked raccoon, dog and orange craft make the scene recognizable, with an appealing sunset palette. Overlapping bodies obscure the riding relationship, and the dog's connection to the controls remains unresolved. Weak water displacement, inconsistent shading and visible shape artifacts limit the finish. Ambiguous attachments do not establish detached limbs or inverted anatomy.

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

CategoryNemotron 3 UltraStep 5 Preview
Task & likeness3.5/104.0/10
Anatomy & construction1.5/104.5/10
Space & placement4.5/103.0/10
Light & reflections2.0/103.5/10
Purposeful detail3.5/104.0/10
Artistry & character1.5/103.5/10
Materials & effects3.0/103.0/10
Visual integrity2.0/103.0/10

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

Same task instructions

Subject construction and spatial relationships.

The judgment

Nemotron 3 Ultra

A recognizable, playful pelican dominates a readable bicycle scene. Its bill and silhouette succeed, but feet below the pedals and confused drivetrain connections weaken the riding action. Local material modeling adds interest; overlapping contours, repetitive detail and inconsistent shadows leave the illustration basic and uneven.

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

CategoryNemotron 3 UltraStep 5 Preview
Task & likeness4.0/103.0/10
Anatomy & construction3.5/103.0/10
Space & placement3.5/103.0/10
Light & reflections4.0/103.0/10
Purposeful detail5.5/104.0/10
Artistry & character4.0/103.0/10
Materials & effects6.0/103.0/10
Visual integrity3.0/102.0/10

Benchmark task

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