STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6.1 Terra Low vs Qwen3.8-27B

Qwen3.8-27B leads GPT-6.1 Terra Low by 10.4 points on StealthMark, 51.7 to 41.3. It leads on 7 of 9 benchmarks, including Foresight, and GPT-6.1 Terra Low on 2, including Latch. Qwen3.8-27B scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

41.3/100Overall rank 35/55
51.7/100Overall rank 15/55

General Intelligence

34.3/100
46.2/100

Visual Intelligence

53.1/100
61.4/100

Open or local

Local modelOpen model · Apache-2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6.1 Terra Low
  • Qwen3.8-27B
  • Other models
  • Median

DATASHEET

Specs and pricing

  • GPT-6.1 Terra Low
  • Qwen3.8-27B
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6.1 Terra Low: No list priceQwen3.8-27B: $1.70$0.42 input
Context windowTokens per request, max output below
GPT-6.1 Terra Low: Not publishedQwen3.8-27B: 1M128K max output
Output speedTokens per second, our measurement
GPT-6.1 Terra Low: Not measuredQwen3.8-27B: 78tokens/s
SizeTotal and active parameters
GPT-6.1 Terra Low: Not disclosedQwen3.8-27B: 27BAll activeEstimated
Developer
Not publishedQwen
Released
Not published14 Aug 2026
Origin
Not publishedChina
Input → output
Not publishedText, image, video → text
Architecture
Not publishedDense causal language model with vision encoder; hybrid Gated DeltaNet and gated attention; MTP-trained

Full datasheets, every price and sourceQwen3.8-27B ↗

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-6.1 Terra Low 36.1/100Rank 26/51

Survived 1 of 3
Foresight: complete playing field
Level 39 ptsTurn 20 / 20

Qwen3.8-27B 63.0/100Rank 7/51

Survived 1 of 3
Foresight: complete playing field
Level 311 ptsTurn 16 / 20

Points per level

LevelGPT-6.1 Terra LowQwen3.8-27B
Level 1Second Thoughts
4 ptsOut of lives
26 ptsSurvived
Level 2Pressure Pot
8 ptsOut of lives
12 ptsOut of lives
Level 3Hide or Flight
9 ptsSurvived
11 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-6.1 Terra Low 62.4/100Rank 23/52

Cleared 4 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

Qwen3.8-27B 38.6/100Rank 32/52

Cleared 2 of 5
Latch: complete playing field
Level 515.8 ptsTurn 31 / 40

Points per level

LevelGPT-6.1 Terra LowQwen3.8-27B
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.2 ptsCleared
9.8 ptsCleared
Level 3Relay vault
18.8 ptsCleared
11.2 ptsFinished early
Level 4Passing bay
10.2 ptsFinished early
13.2 ptsFinished early
Level 5Second thoughts
20.6 ptsCleared
15.8 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

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.

Qwen3.8-27B

The room fills the complete 16:9 frame without visible borders or labels. Central placement fits the wider frame, and the paint colors follow the expected vertical order. Bilateral side images, diminishing echoes and an overlapping floor image provide limited mirror depth. Broad sphere surfaces lack ordered nested room imagery, while planar panel sequences and outer chains remain missing or unresolved. Soft highlights do not establish emitter mapping, while paint attachment and transport history are only partly supported.

Score breakdown

CategoryGPT-6.1 Terra LowQwen3.8-27B
State at 600 ms22.0/2523.0/25
Camera and placement4.0/1513.0/15
Reflections10.0/12024.0/120
Materials and scale6.0/106.5/10
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-6.1 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.

Qwen3.8-27B

A cohesive emerald-and-gold illustration with a gentle expression, flowing robes, luminous halo and three clearly ringed orbs. Limbs remain connected, and the asymmetric legs communicate floating. The rounded face reads somewhat bear-like; the raised palm faces outward rather than upward, and chest-hand fingers are crowded. Clean ornamentation exceeds the comparatively simple anatomical modeling and shading.

Score breakdown

CategoryGPT-6.1 Terra LowQwen3.8-27B
Task & likeness4.0/108.0/10
Anatomy & construction3.5/107.5/10
Space & placement4.5/108.0/10
Light & reflections5.5/107.5/10
Purposeful detail5.5/108.0/10
Artistry & character5.0/107.5/10
Materials & effects5.5/107.5/10
Visual integrity4.0/108.5/10

Benchmark task

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.

Qwen3.8-27B

A floating capybara in ornate robes tests character anatomy, layered fabric and the placement of surrounding luminous forms.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

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.

Qwen3.8-27B

The centered portrait, dark clothing and overlapping hands evoke the Mona Lisa, but replication is weak. The face is excessively elongated, the eyes stare broadly, and the hands reduce to rounded masses with shallow finger marks. Soft shading creates some volume, while the landscape remains indistinct. The precise gold frame is more resolved than the portrait.

Score breakdown

CategoryGPT-6.1 Terra LowQwen3.8-27B
Task & likeness5.0/104.0/10
Anatomy & construction4.5/104.5/10
Space & placement5.0/104.5/10
Light & reflections6.0/105.0/10
Purposeful detail5.0/105.0/10
Artistry & character5.5/105.0/10
Materials & effects5.0/105.0/10
Visual integrity6.0/105.0/10

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-6.1 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.

Qwen3.8-27B

The sweeping palm, glowing sunset and purple-to-orange palette create an appealing beach composition. Birds, animals and reflections fulfill the brief, with clean silhouettes and readable small accents. Schematic anatomy, repetitive shoreline geometry and limited perspective integration constrain depth. Foreground lighting and uniform reflection bars provide atmosphere but little physical coherence.

Score breakdown

CategoryGPT-6.1 Terra LowQwen3.8-27B
Task & likeness8.0/108.5/10
Anatomy & construction5.5/106.5/10
Space & placement5.5/106.0/10
Light & reflections6.5/106.0/10
Purposeful detail6.0/107.0/10
Artistry & character5.0/107.0/10
Materials & effects5.5/106.5/10
Visual integrity7.5/107.0/10

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

GPT-6.1 Terra Low

This benchmark has not been assessed yet.

Qwen3.8-27B

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-6.1 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.

Qwen3.8-27B

The raccoon clearly rides on the dog's back, and the dog reaches the jet ski's steering grip. Cheerful expressions, a bright palette and sweeping wake make the action readable. Anatomy and machinery remain simplified, with overlapping paws and limited seat definition. Flat lighting, sparse surface detail and broad white splash shapes limit depth and finish. A clipped gray fragment interrupts the upper-left corner.

Score breakdown

CategoryGPT-6.1 Terra LowQwen3.8-27B
Task & likeness6.5/108.5/10
Anatomy & construction5.0/106.5/10
Space & placement5.5/107.0/10
Light & reflections4.5/105.5/10
Purposeful detail6.0/106.5/10
Artistry & character5.0/106.5/10
Materials & effects5.0/106.5/10
Visual integrity6.0/107.5/10

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

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.

Qwen3.8-27B

The pelican’s oversized bill, straw hat and flowing scarf create a distinctive focal character against a well-composed coastal sunset. Wheels and frame are readable, but the wings do not reach the steering, overlapping legs obscure separate pedal contacts, and the crank linkage is unclear. Clean vector shapes and restrained shading support an appealing illustration with limited physical depth.

Score breakdown

CategoryGPT-6.1 Terra LowQwen3.8-27B
Task & likeness7.0/108.0/10
Anatomy & construction5.5/105.5/10
Space & placement6.0/107.0/10
Light & reflections5.5/107.0/10
Purposeful detail6.5/107.5/10
Artistry & character6.0/107.5/10
Materials & effects6.0/106.5/10
Visual integrity6.0/108.0/10

Benchmark task

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