STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemini 4 Argon vs GPT-6 Astra

GPT-6 Astra leads Gemini 4 Argon by 7.3 points on StealthMark, 74.7 to 67.4. It leads on 6 of 9 benchmarks, including both games, and Gemini 4 Argon on 3. GPT-6 Astra scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

67.4/100Overall rank 5/53
74.7/100Overall rank 1/53

General Intelligence

63.6/100
73.4/100

Visual Intelligence

74.4/100
77.0/100

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

  • GPT-6 Astra

BENCHMARK BY BENCHMARK

Where each model leads

  • Gemini 4 Argon
  • GPT-6 Astra
  • Other models
  • Median

DATASHEET

Specs and pricing

Gemini 4 Argon is 5× cheaper per output token and runs 2.2× faster in our speed test. GPT-6 Astra scores higher on StealthMark. Both take about 1M tokens of context.

  • Gemini 4 Argon
  • GPT-6 Astra
  • Other models
  • Median
PricePer 1M output tokens, input below
Gemini 4 Argon: $105× cheaper$2 inputGPT-6 Astra: $50$10 input
Context windowTokens per request, max output below
Gemini 4 Argon: 1MTied1M max outputGPT-6 Astra: 1.05MTied128K max output
Output speedTokens per second, our measurement
Gemini 4 Argon: 1442.2× fastertokens/sGPT-6 Astra: 65tokens/s
Developer
GoogleOpenAI
Released
13 Oct 20263 Sep 2026
Origin
United StatesBoth
Input → output
Text, image, audio, video, PDF → textText, image → text
Architecture
Sparse mixture-of-experts (MoE) transformer with native multimodal inputsNot published

Full datasheets, every price and sourceGemini 4 Argon ↗GPT-6 Astra ↗

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.

Gemini 4 Argon 48.6/100Rank 19/47

Survived 1 of 3
Foresight: complete playing field
Level 36 ptsTurn 7 / 20

GPT-6 Astra 76.1/100Rank 2/47

Survived 3 of 3
Foresight: complete playing field
Level 318 ptsTurn 20 / 20

Points per level

LevelGemini 4 ArgonGPT-6 Astra
Level 1Second Thoughts
26 ptsSurvived
27 ptsSurvived
Level 2Pressure Pot
9 ptsOut of lives
11 ptsSurvived
Level 3Hide or Flight
6 ptsOut of lives
18 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.

Gemini 4 Argon 82.6/100Rank 6/48

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

GPT-6 Astra 87.6/100Rank 1/48

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

Points per level

LevelGemini 4 ArgonGPT-6 Astra
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
10.2 ptsClearedFinished early · 1 beacon left
Level 3Relay vault
19.2 ptsCleared
19.2 ptsCleared
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
18.2 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
20.6 ptsCleared

Newton's Mirror

Same task instructions

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

The judgment

Gemini 4 Argon

The central sphere, separate airborne black blob, flattened cyan contact and displaced crimson aftermath support the principal camera and physical-state requirements. Open lateral lanes and initial reflection placements provide partial optical structure, but missing outer chains, sparse nested imagery and incomplete emitter mappings remain substantial limitations. The raised crimson mass also weakens paint-scale fidelity.

GPT-6 Astra

Major placement and the visible contact sequence are convincing. Dense planar light repetition, recognizable spherical panel images and simplified nested sphere motifs provide useful optical structure. Missing outer chains, truncated distant sequences and incorrect bead-like belts still leave the recursive reflections substantially incomplete.

Score breakdown

CategoryGemini 4 ArgonGPT-6 Astra
State at 600 ms24.5/2525.0/25
Camera and placement14.5/1515.0/15
Reflections50.5/12070.0/120
Materials and scale8.5/1010.0/10
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.

The judgment

Gemini 4 Argon

An appealing, controlled illustration with a distinctive buoyant silhouette, expressive comic face and rich luminous colour. The full composition and grounded slipper read clearly. The principal limitation is the crowded raised-foot interaction: paws, toes and lining overlap without making the bent leg or tight fit unmistakable.

GPT-6 Astra

The sixfold silhouette, pale coloring, outward heads and central hexagon closely match the brief. Fine scales and soft shading support rounded volume. However, several crossings have conspicuous rectangular seams and weak contact shadows, making the weave feel assembled. Small heads have limited anatomical definition, and the repetitive texture conveys less organic life than requested.

Score breakdown

CategoryGemini 4 ArgonGPT-6 Astra
Task & likeness7.0/109.0/10
Anatomy & construction6.5/108.0/10
Space & placement7.5/107.5/10
Light & reflections7.5/107.0/10
Purposeful detail8.0/108.0/10
Artistry & character7.0/108.5/10
Materials & effects7.0/108.0/10
Visual integrity7.5/108.5/10

Benchmark task

Gemini 4 Argon

A luminous little dragon struggles with its bedtime slippers while a buoyant tail pulls it upward. The scene tests expressive anatomy, physical contact and the contrast between translucent forms and heavy objects.

GPT-6 Astra

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.

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

Gemini 4 Argon

A coherent, moderately complex Mona Lisa reconstruction with substantial portrait volume, articulated clothing and landscape recession. Specific source features support replication beyond recognition alone. Altered facial likeness, uncertain crossed-hand anatomy and pervasive colored crackle keep the result uneven despite its developed shading and detail.

GPT-6 Astra

The crossed hands, restrained smile, dark clothing and hazy landscape clearly recall the Mona Lisa. Replication is limited by the frontal, elongated face, schematic eyes and stiff fingers. Soft shading gives basic volume, but broad garment shapes and angular scenery lack the original’s nuanced depth and painterly transitions. The frame and composition are controlled; surface grain adds texture without resolving the simplified drawing.

Score breakdown

CategoryGemini 4 ArgonGPT-6 Astra
Task & likeness6.5/106.5/10
Anatomy & construction6.5/106.5/10
Space & placement6.5/106.5/10
Light & reflections7.0/106.5/10
Purposeful detail6.0/106.5/10
Artistry & character6.5/107.0/10
Materials & effects7.0/107.0/10
Visual integrity7.0/107.5/10

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

Gemini 4 Argon

A strong decorative beach illustration with controlled color, intricate silhouettes and abundant playful detail. Connected dolphin forms and recognizable equipment support its construction, while the aligned sunset reflection anchors the scene. Compressed wave depth, ambiguous foreground support and uneven reflection specificity limit physical coherence. The saved comparisons support retaining the category assessments.

GPT-6 Astra

A richly composed sunset beach illustration with cohesive peach, mauve and teal colors. Sweeping palm fronds, a scalloped umbrella and curved shorelines frame the sun and its aligned reflection. Distinct animal silhouettes and carefully distributed beach details reward inspection. Simplified human and dog anatomy, slight dolphin splash cues and inconsistent equipment shadows limit physical conviction.

Score breakdown

CategoryGemini 4 ArgonGPT-6 Astra
Task & likeness9.0/109.0/10
Anatomy & construction7.5/107.5/10
Space & placement8.5/108.5/10
Light & reflections8.5/107.5/10
Purposeful detail9.0/108.5/10
Artistry & character8.0/108.5/10
Materials & effects8.0/107.5/10
Visual integrity8.0/107.5/10

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.

The judgment

Gemini 4 Argon

This benchmark has not been assessed yet.

GPT-6 Astra

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

Gemini 4 Argon

An accomplished illustration with expressive characters, intricate spray and strong depth. Direct back seating, steering connections and hull-water contact are only partly demonstrated. Clean graphic execution and purposeful detail remain strengths, while shadows and reflections provide limited physical grounding.

GPT-6 Astra

Expressive animals, a balanced sunset composition and sweeping wake make an appealing illustration. The raccoon rides the dog's back, and the dog's connected foreleg reaches the controls. The compact steering assembly and layered paws are less clearly constructed. Lighting remains mostly flat, with little shadow or sun reflection. Clean contours and purposeful details support strong illustrative execution.

Score breakdown

CategoryGemini 4 ArgonGPT-6 Astra
Task & likeness8.5/108.5/10
Anatomy & construction8.0/107.5/10
Space & placement7.5/108.0/10
Light & reflections7.5/106.5/10
Purposeful detail8.5/108.0/10
Artistry & character8.5/107.5/10
Materials & effects8.0/108.0/10
Visual integrity8.0/108.5/10

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

Same task instructions

Subject construction and spatial relationships.

The judgment

Gemini 4 Argon

An expressive, detailed illustration with controlled gradients and coherent environmental depth. Continuous body contours and connected bicycle components establish competent construction. Steering grip and pedal engagement remain less explicit than the decorative details and wheel placement. These contact uncertainties limit action and placement credit without establishing broken anatomy.

GPT-6 Astra

The pelican's long bill, flowing scarf and warm coastal palette create a charming, balanced illustration. Wheels, spokes and frame are largely coherent, but neither wing reaches the handlebars, and the rear leg's pedal contact is unclear. Flat lighting and simplified surfaces limit depth despite clean outlines and attractive feather detail.

Score breakdown

CategoryGemini 4 ArgonGPT-6 Astra
Task & likeness9.0/108.0/10
Anatomy & construction8.5/107.0/10
Space & placement8.0/107.5/10
Light & reflections8.0/107.0/10
Purposeful detail8.5/108.0/10
Artistry & character8.5/108.0/10
Materials & effects8.5/107.5/10
Visual integrity8.5/108.0/10

Benchmark task

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