STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6 Sol vs Nemotron 3 Ultra

GPT-6 Sol leads Nemotron 3 Ultra by 35.3 points on StealthMark, 52.0 to 16.7. It leads on all 9 benchmarks. GPT-6 Sol 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

52.0/100Overall rank 17/58
16.7/100Overall rank 55/58

General Intelligence

46.2/100
12.2/100

Visual Intelligence

62.4/100
26.5/100

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

  • GPT-6 Sol

Cost efficiency

How much Performance you get for your money.

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6 Sol
  • Nemotron 3 Ultra
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-6 Sol scores higher on StealthMark. Nemotron 3 Ultra is 4.2× cheaper per output token and runs 1.5× faster in our speed test. Both take about 1.05M tokens of context.

  • GPT-6 Sol
  • Nemotron 3 Ultra
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6 Sol: $10$2 inputNemotron 3 Ultra: $2.404.2× cheaper$0.60 input
Context windowTokens per request, max output below
GPT-6 Sol: 1.05MTied128K max outputNemotron 3 Ultra: 1MTied
Output speedTokens per second, our measurement
GPT-6 Sol: 91tokens/sNemotron 3 Ultra: 1391.5× fastertokens/s
SizeTotal and active parameters
GPT-6 Sol: Not disclosedNemotron 3 Ultra: 550B55B active
Developer
OpenAINVIDIA
Released
22 Sep 20264 Jun 2026
Origin
United StatesBoth
Input → output
Text, image → textText → text
Architecture
Not publishedLatentMoE: Mamba-2 + MoE + Attention hybrid with Multi-Token Prediction

Full datasheets, every price and sourceGPT-6 Sol ↗Nemotron 3 Ultra ↗

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 Sol 30.4/100Rank 33/54

Survived 0 of 3
Foresight: complete playing field
Level 36 ptsTurn 7 / 20

Nemotron 3 Ultra 16.9/100Rank 48/54

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 17 / 20

Points per level

LevelGPT-6 SolNemotron 3 Ultra
Level 1Second Thoughts
17 ptsOut of lives
4 ptsOut of lives
Level 2Pressure Pot
5 ptsOut of lives
4 ptsOut of lives
Level 3Hide or Flight
6 ptsOut of lives
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.

GPT-6 Sol 76.6/100Rank 14/55

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

Nemotron 3 Ultra 5.0/100Rank 49/554 of 5 levels

4 of 5 played
Latch: complete playing field
Level 413.8 ptsTurn 21 / 40

Points per level

LevelGPT-6 SolNemotron 3 Ultra
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
3.2 ptsFinished early
Level 3Relay vault
18.4 ptsCleared
7.4 ptsFinished early
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
13.8 ptsFinished early
Level 5Second thoughts
20.6 ptsCleared
Not played

Newton's Mirror

Same task instructions

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

The judgment

GPT-6 Sol

The centered sphere, separate airborne black form and color ordering support scene recognition. Rounded shading and curved rims provide readable volume and gloss. Shrinking side images, a floor counterpart and curved lamp highlights provide isolated reflection cues, but broad bands and sparse repetitions leave nested room imagery, outer chains and ordered emitter mapping unsupported. Vertical framing departs from the prescribed view, while paint contact, transport and solid-metal appearance remain weak or uncertain.

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.

Score breakdown

CategoryGPT-6 SolNemotron 3 Ultra
State at 600 ms19.0/252.0/25
Camera and placement12.0/153.5/15
Reflections8.0/1204.5/120
Materials and scale6.5/103.0/10
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 Sol

Six evenly spaced lobes, small outward-facing heads and a regular hexagonal opening make the motif immediately readable. The central angular band merges several intersections, weakening the alternating weave. Pale shading gives modest volume, but scales are sparse and repetitive, crossing shadows are weak, and the heads have limited anatomical definition.

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.

Score breakdown

CategoryGPT-6 SolNemotron 3 Ultra
Task & likeness7.5/104.0/10
Anatomy & construction6.5/104.0/10
Space & placement6.5/105.5/10
Light & reflections6.0/105.0/10
Purposeful detail6.5/104.0/10
Artistry & character7.0/103.0/10
Materials & effects5.5/104.0/10
Visual integrity6.0/104.5/10

Benchmark task

GPT-6 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.

Nemotron 3 Ultra

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

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

GPT-6 Sol

A recognizable, coherent simplification with rounded facial shading, an asymmetric veil and readable forearm overlap. Selective eye, neckline, hair and bridge details enrich the broad shapes. The frontal pose, oversized face, schematic hands and limited fabric construction constrain replication and drawing complexity.

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.

Score breakdown

CategoryGPT-6 SolNemotron 3 Ultra
Task & likeness5.0/100.5/10
Anatomy & construction5.0/100.0/10
Space & placement5.0/101.0/10
Light & reflections6.0/100.5/10
Purposeful detail4.5/100.5/10
Artistry & character5.5/101.5/10
Materials & effects5.5/100.0/10
Visual integrity6.0/100.5/10

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

GPT-6 Sol

A coherent sunset illustration with clear prompt fulfilment, varied readable details and controlled atmospheric colour. Connected animal silhouettes and supported equipment withstand inspection. Simplified anatomy, ambiguous animal depth, schematic reflections and weakly directional shadows constrain its physical sophistication.

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.

Score breakdown

CategoryGPT-6 SolNemotron 3 Ultra
Task & likeness8.5/106.5/10
Anatomy & construction6.0/103.0/10
Space & placement6.0/105.0/10
Light & reflections6.0/101.5/10
Purposeful detail7.5/104.5/10
Artistry & character6.5/103.0/10
Materials & effects6.5/102.5/10
Visual integrity7.5/106.5/10

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 Sol

This benchmark has not been assessed yet.

Nemotron 3 Ultra

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

GPT-6 Sol

The raccoon rides the dog's back, and the dog's connected foreleg reaches the steering grip. Expressive faces, a cohesive palette and sweeping wake make an appealing illustration. Vehicle construction and seating remain simplified; broad splash ribbons convey speed more convincingly than physical displacement. The sun has little corresponding reflection or effect on the subjects.

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.

Score breakdown

CategoryGPT-6 SolNemotron 3 Ultra
Task & likeness7.5/103.5/10
Anatomy & construction6.5/101.5/10
Space & placement7.5/104.5/10
Light & reflections6.0/102.0/10
Purposeful detail7.5/103.5/10
Artistry & character6.5/101.5/10
Materials & effects7.5/103.0/10
Visual integrity8.0/102.0/10

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

GPT-6 Sol

The pelican reads clearly, with an expressive face, generous bill and appealing pastel composition. Spokes, basket weave and feather contours are carefully organized. Both legs connect to the body, though joint definition and pedal contacts are simplified. Consistent wheel placement and a ground shadow establish support; restrained shading gives limited volume.

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.

Score breakdown

CategoryGPT-6 SolNemotron 3 Ultra
Task & likeness9.0/104.0/10
Anatomy & construction7.5/103.5/10
Space & placement8.0/103.5/10
Light & reflections7.0/104.0/10
Purposeful detail8.0/105.5/10
Artistry & character8.5/104.0/10
Materials & effects7.0/106.0/10
Visual integrity8.5/103.0/10

Benchmark task

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