Claude Haiku 5.5 34.4/100Rank 28/51

STEALTHMARK · HEAD TO HEAD
All comparisons ↗Claude Haiku 5.5 leads GPT-6.1 Terra Low by 8.2 points on StealthMark, 49.5 to 41.3. It leads on 6 of 9 benchmarks, including Latch, and GPT-6.1 Terra Low on 3, including Foresight. Claude Haiku 5.5 scores higher on Newton's Mirror, with its largest category advantage in reflections.
See the difference ↘BENCHMARK BY BENCHMARK
DATASHEET
Full datasheets, every price and sourceClaude Haiku 5.5 ↗
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.


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.


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


Claude Haiku 5.5
The centered sphere, compact airborne black blob and differentiated cyan/crimson interaction support substantial state and placement credit. The few recognizable sphere and panel images establish limited optical relationships, but most of the required mirror system is missing. Rounded volume and localized paint warrant substantial material credit despite the soft, illustrative finish.
GPT-6.1 Terra Low
Deformed colored paint and a separate airborne black body establish readable interaction history. Cyan has travelled too far, framing differs substantially, and the mirror system supplies only elementary bands and oval copies. Missing recursive geometry, nested spherical imagery and emitter mapping remain the dominant weaknesses.
| Category | Claude Haiku 5.5 | GPT-6.1 Terra Low |
|---|---|---|
| State at 600 ms | 25.0/25 | 22.0/25 |
| Camera and placement | 8.0/15 | 4.0/15 |
| Reflections | 24.5/120 | 10.0/120 |
| Materials and scale | 7.5/10 | 6.0/10 |
| Floor-damage reward | 0.0/10 | 0.0/10 |
A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.
Visual construction and creative interpretation.


Claude Haiku 5.5
A coherent coral squid emblem with a compact mantle, restrained face and clean centered presentation. Its radial silhouette and floating placement work, but sharp arm tips, crowded roots and sparse surface modeling limit softness, construction and finish.
GPT-6.1 Terra Low
Six attached outward-facing heads, delicate scales and soft ivory shading establish an orderly decorative motif. Separate paddle-shaped bodies replace the required interlocking loops and leave no enclosed central hexagon. Surface detail provides interest, but repeated simple forms, schematic faces and limited anatomical modeling constrain the result.
| Category | Claude Haiku 5.5 | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 6.5/10 | 4.0/10 |
| Anatomy & construction | 4.0/10 | 3.5/10 |
| Space & placement | 6.5/10 | 4.5/10 |
| Light & reflections | 4.0/10 | 5.5/10 |
| Purposeful detail | 3.5/10 | 5.5/10 |
| Artistry & character | 3.5/10 | 5.0/10 |
| Materials & effects | 4.5/10 | 5.5/10 |
| Visual integrity | 7.0/10 | 4.0/10 |
Claude Haiku 5.5
A coral squid with spreading arms tests connected anatomy, balanced composition and soft surface shading.
GPT-6.1 Terra Low
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.
Precise visual recall and portrait reconstruction.


Claude Haiku 5.5
A recognizable but basic Mona Lisa reinterpretation. Clean contours and smooth facial lighting provide coherence and volume. Replication remains limited by the frontal pose, elongated neck, schematic expression, unresolved crossed hands and sparse landscape. Lighting is more successful than anatomical construction and purposeful detail.
GPT-6.1 Terra Low
A recognizable, coherent portrait with purposeful facial detail, warm local volume and layered scenery. The frontal pose, enlarged face, merged hands and shallow clothing construction substantially limit replication and drawing skill. The visible successes support retaining the current assessment.
| Category | Claude Haiku 5.5 | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 3.0/10 | 5.0/10 |
| Anatomy & construction | 4.0/10 | 4.5/10 |
| Space & placement | 4.0/10 | 5.0/10 |
| Light & reflections | 5.5/10 | 6.0/10 |
| Purposeful detail | 2.5/10 | 5.0/10 |
| Artistry & character | 3.5/10 | 5.5/10 |
| Materials & effects | 2.5/10 | 5.0/10 |
| Visual integrity | 5.5/10 | 6.0/10 |
An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.
Creativity, perspective and visual beauty.


Claude Haiku 5.5
A cheerful, coherent beach illustration with attractive sunset colors, readable accessories and clean silhouettes. Its sun and sailboat reflections establish useful physical relationships. Simple animal construction, flattened foreground placement, sparse directional shadows and minimally differentiated surfaces limit its drawing refinement.
GPT-6.1 Terra Low
A coherent sunset scene demonstrates the beach, animals, birds and reflections. Flowing silhouettes, warm color transitions and intact attachments are its strongest properties. Simplified anatomy, the turtle's elevated viewing angle and symbolic surface effects constrain drawing complexity and physical depth.
| Category | Claude Haiku 5.5 | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 8.5/10 | 8.0/10 |
| Anatomy & construction | 6.5/10 | 5.5/10 |
| Space & placement | 7.0/10 | 5.5/10 |
| Light & reflections | 7.0/10 | 6.5/10 |
| Purposeful detail | 7.0/10 | 6.0/10 |
| Artistry & character | 6.0/10 | 5.0/10 |
| Materials & effects | 6.0/10 | 5.5/10 |
| Visual integrity | 8.5/10 | 7.5/10 |
A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.
Physical reasoning, light and visual reconstruction.


Claude Haiku 5.5
This benchmark has not been assessed yet.
GPT-6.1 Terra Low
This benchmark has not been assessed yet.
A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.
Scene composition and interacting subjects.


Claude Haiku 5.5
A tidy, appealing cartoon with recognizable animals and a pleasing sunset palette. Steering lacks visible controls, while schematic limbs and uncertain raccoon support weaken the requested interaction. Shallow vehicle construction, flat character lighting and modest displacement limit physical coherence. Clean shapes and readable identifying details remain strengths.
GPT-6.1 Terra Low
Recognizable animals, a coherent craft and sweeping wake make an appealing cartoon. Basic limb construction, weakly demonstrated raccoon seating and limited shared perspective constrain the scene. Small identifying details work well, while lighting and materials remain broadly graphic.
| Category | Claude Haiku 5.5 | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 4.0/10 | 6.5/10 |
| Anatomy & construction | 3.5/10 | 5.0/10 |
| Space & placement | 5.5/10 | 5.5/10 |
| Light & reflections | 4.0/10 | 4.5/10 |
| Purposeful detail | 5.5/10 | 6.0/10 |
| Artistry & character | 4.5/10 | 5.0/10 |
| Materials & effects | 5.5/10 | 5.0/10 |
| Visual integrity | 4.5/10 | 6.0/10 |
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.
Subject construction and spatial relationships.


Claude Haiku 5.5
A cheerful, recognizable illustration with clean contours and a balanced warm palette. Aligned wheels and readable frame geometry establish the bicycle, but shoulder construction, feet and steering contact remain imprecise. Sparse drivetrain detail, flat materials and absent grounding shadows limit anatomical and spatial conviction.
GPT-6.1 Terra Low
A coherent coastal illustration with a distinctive pelican, controlled contours and clearly organised bicycle wheels. Visible saddle support and shaped neck and wing contours earn credit beyond basic geometric construction. Rubbery legs, unresolved pedal contacts and absent steering contact limit the riding action. Lighting and materials remain restrained and spatially shallow.
| Category | Claude Haiku 5.5 | GPT-6.1 Terra Low |
|---|---|---|
| Task & likeness | 8.0/10 | 7.0/10 |
| Anatomy & construction | 5.5/10 | 5.5/10 |
| Space & placement | 6.5/10 | 6.0/10 |
| Light & reflections | 5.0/10 | 5.5/10 |
| Purposeful detail | 6.0/10 | 6.5/10 |
| Artistry & character | 5.0/10 | 6.0/10 |
| Materials & effects | 5.0/10 | 6.0/10 |
| Visual integrity | 8.0/10 | 6.0/10 |
A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.