STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Fledge Alpha vs GPT-6 Luna

GPT-6 Luna leads Fledge Alpha by 3.3 points on StealthMark, 39.1 to 35.8. It leads on 4 of the 7 benchmarks with results for both and Fledge Alpha on 3. GPT-6 Luna scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
Model guide ↗
All results ↗

Overall StealthMark

35.8/100Overall rank 45/58
39.1/100Overall rank 40/58

General Intelligence

27.1/100
31.3/100

Visual Intelligence

45.2/100
52.0/100

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

  • Fledge AlphaMulti-step reasoning not measured

Cost efficiency

How much Performance you get for your money.

  • Fledge AlphaNot measured

Open or local

BENCHMARK BY BENCHMARK

Where each model leads

  • Fledge Alpha
  • GPT-6 Luna
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-6 Luna scores higher on StealthMark and runs 2.1× faster in our speed test.

  • Fledge Alpha
  • GPT-6 Luna
  • Other models
  • Median
PricePer 1M output tokens, input below
Fledge Alpha: No list priceGPT-6 Luna: $0.50$0.10 input
Context windowTokens per request, max output below
Fledge Alpha: Not publishedGPT-6 Luna: 1.05M128K max output
Output speedTokens per second, our measurement
Fledge Alpha: 63tokens/sGPT-6 Luna: 1312.1× fastertokens/s
Developer
Not publishedOpenAI
Released
Not published22 Sep 2026
Origin
Not publishedUnited States
Input → output
Not publishedText, image → text

Full datasheets, every price and sourceGPT-6 Luna ↗

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 Luna 29.8/100Rank 37/54

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

Points per level

LevelFledge AlphaGPT-6 Luna
Level 1Second Thoughts
No run
15 ptsOut of lives
Level 2Pressure Pot
No run
5 ptsOut of lives
Level 3Hide or Flight
No run
6 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 Luna 44.0/100Rank 31/55

Cleared 4 of 5
Latch: complete playing field
Level 513 ptsTurn 15 / 40

Points per level

LevelFledge AlphaGPT-6 Luna
Level 1Hold the door
No run
5.2 ptsCleared
Level 2Crossfeed
No run
8.8 ptsClearedFinished early · 1 beacon left
Level 3Relay vault
No run
17 ptsCleared1 beacon left
Level 4Passing bay
No run
15.8 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
No run
13 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

Fledge Alpha

The candidate communicates a round metallic sphere, three paint colors and a separate airborne black blob. Its hovering support relationship, displaced framing and unresolved paint interaction limit physical credit. Sparse planar light ghosts and a soft sphere highlight provide little evidence for the required wall/floor repetitions and curved nested mirror imagery.

GPT-6 Luna

The schematic scene supports the paint contact order and compact paint scale. Its low, undersized main sphere and incorrectly placed wall images depart from the reference geometry. A few shrinking wall images provide limited optical organization, while absent lateral recursion and outer chains, broad sphere ribbons and isolated panel highlights leave most nested room and emitter mapping undeveloped.

Score breakdown

CategoryFledge AlphaGPT-6 Luna
State at 600 ms9.0/2522.0/25
Camera and placement5.0/153.5/15
Reflections7.5/1205.0/120
Materials and scale3.5/107.0/10
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

Fledge Alpha

A coherent, appealing mascot with expressive eyes, a cheerful beak and a readable swept-back silhouette. Its larger forward foot and trailing feathers suggest a running stride, but the upright body, stiff legs and minimally articulated feet limit convincing motion. Clean flat shapes suit the brief, while uneven feather junctions and incomplete cream accents reduce polish.

GPT-6 Luna

Sixfold symmetry, pale coloring and six outward-facing heads establish the motif. However, every neck floats clear of the knot. Squared outer sections replace the required semicircular lobes, and the large stepped opening lacks a regular hexagonal contour. Repeated scales and soft shading suggest skin, but translucent crossings and doubled edges weaken the living, interwoven construction.

Score breakdown

CategoryFledge AlphaGPT-6 Luna
Task & likeness7.5/104.5/10
Anatomy & construction6.5/103.5/10
Space & placement7.0/105.5/10
Light & reflections5.5/105.0/10
Purposeful detail6.5/105.0/10
Artistry & character4.0/105.0/10
Materials & effects6.0/105.0/10
Visual integrity6.5/104.5/10

Benchmark task

Fledge Alpha

An eager young seabird running toward the viewer tests expressive anatomy, balance and a convincing forward-moving pose.

GPT-6 Luna

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

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Fledge Alpha

A recognizable but basic Mona Lisa reinterpretation with a coherent silhouette and subdued palette. Curtain-like hair obscures much of the face, while elongated facial construction and oversized, minimally articulated hands substantially weaken replication. Soft shading supplies modest volume, but anatomy, landscape depth and purposeful detail remain underdeveloped.

GPT-6 Luna

The dark veil, crossed arms, restrained smile and layered landscape clearly evoke Mona Lisa. Clean contours and muted colors create a coherent illustration. Replication is limited by enlarged, outlined eyes, simplified facial volume, broad shoulders and indistinct overlapping hands. Gradients suggest depth, but lack the original's subtle painterly transitions.

Score breakdown

CategoryFledge AlphaGPT-6 Luna
Task & likeness3.0/104.5/10
Anatomy & construction3.0/104.0/10
Space & placement2.5/105.5/10
Light & reflections2.5/105.0/10
Purposeful detail3.0/105.0/10
Artistry & character3.0/104.5/10
Materials & effects2.5/105.0/10
Visual integrity2.5/106.0/10

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

Fledge Alpha

A cheerful, recognizable sunset beach with a cohesive warm palette and clear accessories. Simple construction, uncertain palm support, an ambiguous upper boundary and schematic reflections limit depth and finish. The scene communicates its subject successfully but lacks the developed forms, lighting and detail of exceptional illustration.

GPT-6 Luna

The warm sky, layered sea and framing palms create an appealing beach composition. Animals, birds, toys and reflected sunlight fulfill the brief. Human anatomy remains schematic, and simplified figures offer limited expression. Missing shadows and the dolphin's splashless jump weaken physical grounding, while clean silhouettes and readable small details support the illustration.

Score breakdown

CategoryFledge AlphaGPT-6 Luna
Task & likeness7.5/107.5/10
Anatomy & construction4.0/105.0/10
Space & placement5.5/107.5/10
Light & reflections5.0/105.0/10
Purposeful detail3.0/107.0/10
Artistry & character3.0/105.0/10
Materials & effects2.5/106.5/10
Visual integrity4.0/106.0/10

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

Fledge Alpha

This benchmark has not been assessed yet.

GPT-6 Luna

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

Fledge Alpha

An appealing sunset illustration with recognizable characters and a clear riding action. Color, expression and silhouette are stronger than anatomical construction: overlapping paws obscure support, the dog's steering limb is simplified, and the vehicle controls lack definition. The wake conveys movement, while lighting and water reflections remain decorative.

GPT-6 Luna

Expressive faces, warm sunset colors and clean silhouettes create an appealing illustration. The raccoon sits on the dog's back, but the dog's grip and steering linkage remain unclear. The broad hull resembles a speedboat, and flat shading, absent sun reflections and modest water displacement limit depth and motion.

Score breakdown

CategoryFledge AlphaGPT-6 Luna
Task & likeness8.5/108.0/10
Anatomy & construction5.5/105.5/10
Space & placement7.5/107.5/10
Light & reflections6.5/106.0/10
Purposeful detail7.0/107.0/10
Artistry & character5.5/105.5/10
Materials & effects7.0/106.5/10
Visual integrity4.5/105.0/10

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

Fledge Alpha

A clear, cheerful illustration with a recognizable pelican, coherent bicycle silhouette and tidy composition. Simplified leg articulation, steering contact, mechanical detail and lighting keep it at a competent illustrative level.

GPT-6 Luna

The pelican’s distinctive bill and the coordinated vintage poster palette make an appealing illustration. Circular wheels, orderly spokes and clean lettering strengthen the design. Riding mechanics are less convincing: neither wing reaches the handlebars, pedal contact is ambiguous, and the drivetrain is incomplete. The wheels sit against water without a clear supporting surface. Flat lighting limits volume.

Score breakdown

CategoryFledge AlphaGPT-6 Luna
Task & likeness8.0/108.0/10
Anatomy & construction6.0/105.0/10
Space & placement6.5/106.5/10
Light & reflections4.5/106.5/10
Purposeful detail5.5/107.5/10
Artistry & character5.0/106.5/10
Materials & effects5.5/106.5/10
Visual integrity6.5/107.0/10

Benchmark task

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