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 ↘Overall StealthMark
General Intelligence
Visual Intelligence
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
BENCHMARK BY BENCHMARK
Where each model leads
- Fledge Alpha
- GPT-6 Luna
- Other models
- Median
Games
SVG
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
- 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 ↗
Foresight
Play Foresight yourselfAnticipating 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

Points per level
Latch
Play Latch yourselfCooperative 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.
Fledge AlphaNo run
GPT-6 Luna 44.0/100Rank 31/55

Points per level
Newton's Mirror
Same task instructionsPhysics, perspective and recursive reflections, tested together. Explore the test ↗
Fledge Alpha 16.4/100 Rank 49/58

GPT-6 Luna 26.6/100 Rank 38/58

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
| Category | Fledge Alpha | GPT-6 Luna |
|---|---|---|
| State at 600 ms | 9.0/25 | 22.0/25 |
| Camera and placement | 5.0/15 | 3.5/15 |
| Reflections | 7.5/120 | 5.0/120 |
| Materials and scale | 3.5/10 | 7.0/10 |
| Floor-damage reward | 0.0/10 | 0.0/10 |
Benchmark task
A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.
Selfie
Different task instructionsVisual construction and creative interpretation.
Fledge Alpha 61.1/100 Rank 33/58

GPT-6 Luna 45.6/100 Rank 48/58

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
| Category | Fledge Alpha | GPT-6 Luna |
|---|---|---|
| Task & likeness | 7.5/10 | 4.5/10 |
| Anatomy & construction | 6.5/10 | 3.5/10 |
| Space & placement | 7.0/10 | 5.5/10 |
| Light & reflections | 5.5/10 | 5.0/10 |
| Purposeful detail | 6.5/10 | 5.0/10 |
| Artistry & character | 4.0/10 | 5.0/10 |
| Materials & effects | 6.0/10 | 5.0/10 |
| Visual integrity | 6.5/10 | 4.5/10 |
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 instructionsPrecise visual recall and portrait reconstruction.
Fledge Alpha 28.3/100 Rank 41/58

GPT-6 Luna 47.4/100 Rank 23/58

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
| Category | Fledge Alpha | GPT-6 Luna |
|---|---|---|
| Task & likeness | 3.0/10 | 4.5/10 |
| Anatomy & construction | 3.0/10 | 4.0/10 |
| Space & placement | 2.5/10 | 5.5/10 |
| Light & reflections | 2.5/10 | 5.0/10 |
| Purposeful detail | 3.0/10 | 5.0/10 |
| Artistry & character | 3.0/10 | 4.5/10 |
| Materials & effects | 2.5/10 | 5.0/10 |
| Visual integrity | 2.5/10 | 6.0/10 |
Benchmark task
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
Beach
Different task instructionsCreativity, perspective and visual beauty.
Fledge Alpha 43.4/100 Rank 50/58

GPT-6 Luna 59.1/100 Rank 36/58

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
| Category | Fledge Alpha | GPT-6 Luna |
|---|---|---|
| Task & likeness | 7.5/10 | 7.5/10 |
| Anatomy & construction | 4.0/10 | 5.0/10 |
| Space & placement | 5.5/10 | 7.5/10 |
| Light & reflections | 5.0/10 | 5.0/10 |
| Purposeful detail | 3.0/10 | 7.0/10 |
| Artistry & character | 3.0/10 | 5.0/10 |
| Materials & effects | 2.5/10 | 6.5/10 |
| Visual integrity | 4.0/10 | 6.0/10 |
Benchmark task
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Ground Truth
Same task instructionsPhysical reasoning, light and visual reconstruction.
Fledge Alpha 36.8/100 Rank 36/58

GPT-6 Luna 30.3/100 Rank 42/58

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 instructionsScene composition and interacting subjects.
Fledge Alpha 63.4/100 Rank 22/58

GPT-6 Luna 62.2/100 Rank 25/58

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
| Category | Fledge Alpha | GPT-6 Luna |
|---|---|---|
| Task & likeness | 8.5/10 | 8.0/10 |
| Anatomy & construction | 5.5/10 | 5.5/10 |
| Space & placement | 7.5/10 | 7.5/10 |
| Light & reflections | 6.5/10 | 6.0/10 |
| Purposeful detail | 7.0/10 | 7.0/10 |
| Artistry & character | 5.5/10 | 5.5/10 |
| Materials & effects | 7.0/10 | 6.5/10 |
| Visual integrity | 4.5/10 | 5.0/10 |
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 instructionsSubject construction and spatial relationships.
Fledge Alpha 60.5/100 Rank 38/58

GPT-6 Luna 65.8/100 Rank 31/58

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
| Category | Fledge Alpha | GPT-6 Luna |
|---|---|---|
| Task & likeness | 8.0/10 | 8.0/10 |
| Anatomy & construction | 6.0/10 | 5.0/10 |
| Space & placement | 6.5/10 | 6.5/10 |
| Light & reflections | 4.5/10 | 6.5/10 |
| Purposeful detail | 5.5/10 | 7.5/10 |
| Artistry & character | 5.0/10 | 6.5/10 |
| Materials & effects | 5.5/10 | 6.5/10 |
| Visual integrity | 6.5/10 | 7.0/10 |
Benchmark task
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.