STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6.1 Terra vs Qwen3.5-9B

GPT-6.1 Terra leads Qwen3.5-9B by 49.5 points on StealthMark, 60.4 to 10.9. It leads on all 9 benchmarks. GPT-6.1 Terra scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

60.4/100Overall rank 9/54
10.9/100Overall rank 54/54

General Intelligence

58.0/100
7.9/100

Visual Intelligence

64.9/100
15.6/100

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

Open or local

Local modelOpen model · Apache-2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6.1 Terra
  • Qwen3.5-9B
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-6.1 Terra scores higher on StealthMark. Qwen3.5-9B is 20× cheaper per output token. Both take about 1.05M tokens of context.

  • GPT-6.1 Terra
  • Qwen3.5-9B
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6.1 Terra: $5$1 inputQwen3.5-9B: $0.2520× cheaper$0.17 input
Context windowTokens per request, max output below
GPT-6.1 Terra: 1.05MTied128K max outputQwen3.5-9B: 1.01MTied
Output speedTokens per second, our measurement
GPT-6.1 Terra: Not measuredQwen3.5-9B: 161tokens/s
SizeTotal and active parameters
GPT-6.1 Terra: Not disclosedQwen3.5-9B: 9BAll activeEstimated
Developer
OpenAIQwen
Released
26 Oct 20262 Mar 2026
Origin
United StatesChina
Input → output
Text, image → textText, image, video → text
Architecture
Not publishedDense causal language model with vision encoder; Gated DeltaNet + gated attention; MTP-trained

Full datasheets, every price and sourceGPT-6.1 Terra ↗Qwen3.5-9B ↗

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 62.0/100Rank 9/50

Survived 2 of 3
Foresight: complete playing field
Level 315 ptsTurn 20 / 20

Qwen3.5-9B 12.8/100Rank 46/50

Survived 0 of 3
Foresight: complete playing field
Level 32 ptsTurn 8 / 20

Points per level

LevelGPT-6.1 TerraQwen3.5-9B
Level 1Second Thoughts
21 ptsSurvived
4 ptsOut of lives
Level 2Pressure Pot
9 ptsOut of lives
4 ptsOut of lives
Level 3Hide or Flight
15 ptsSurvived
2 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 77.7/100Rank 12/51

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

Qwen3.5-9B 3.8/100Rank 46/51

Cleared 1 of 5
Latch: complete playing field
Level 54.4 ptsTurn 33 / 40

Points per level

LevelGPT-6.1 TerraQwen3.5-9B
Level 1Hold the door
5.2 ptsCleared
5 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
3.8 ptsFinished early
Level 3Relay vault
19.2 ptsCleared
1.2 ptsFinished early
Level 4Passing bay
17.8 ptsClearedFinished early · 3 beacons left
0.2 ptsFinished early
Level 5Second thoughts
20.6 ptsCleared
4.4 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

GPT-6.1 Terra

The sphere, airborne black and first reflected silhouettes preserve important geometry within the portrait frame. Paint deformation, contact order and forward transport are supported, with a small crimson endpoint overshoot. Major optical omissions dominate: short finite reflection sequences and smooth bands replace extensive, spatially ordered mirror imagery. Dark gloss and crisp upper emitter shapes provide partial material credit.

Qwen3.5-9B

Horizontal centering and a separate airborne black blob are visible. Cyan's recent contact and crimson's forward transport are insufficiently demonstrated, while sphere support remains obscured. The enlarged, lowered sphere substantially changes the composition. The wall and floor sphere images, recursive room structure and curved emitter mappings are almost entirely missing.

Score breakdown

CategoryGPT-6.1 TerraQwen3.5-9B
State at 600 ms23.0/253.0/25
Camera and placement11.0/154.5/15
Reflections33.0/1202.0/120
Materials and scale7.5/103.0/10
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

GPT-6.1 Terra

A balanced serpent emblem with six attached outward heads, delicate scales and softly rounded bodies. Its compact silhouette reads clearly, but central routing does not establish every alternating crossing or crisp inward corner. Repetitive texture, limited facial anatomy and weak contact shadows constrain its organic character.

Qwen3.5-9B

Glowing teal spheres and a harmonious palette provide visible strengths, but the central character remains seriously unresolved. A large gap separates head and torso, limbs cannot be traced, and scattered garment shapes fail to establish the ornate costume. The foreground mound replaces the tall enclosing arch. Clean primitive edges do not repair these construction failures.

Score breakdown

CategoryGPT-6.1 TerraQwen3.5-9B
Task & likeness7.5/103.0/10
Anatomy & construction6.5/102.0/10
Space & placement6.5/103.0/10
Light & reflections6.0/103.5/10
Purposeful detail6.5/102.0/10
Artistry & character6.5/102.0/10
Materials & effects6.0/104.0/10
Visual integrity6.0/103.0/10

Benchmark task

GPT-6.1 Terra

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.

Qwen3.5-9B

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

A recognizable interpretation with developed facial shading, shaped sleeve folds and purposeful small features. These strengths support modest upward calibration, while the frontal torso, elongated proportions, schematic finger joints and unresolved seated support keep replication and construction uneven.

Qwen3.5-9B

A centered dark oval with sparse facial marks forms a simple graphic face, but scarcely replicates the Mona Lisa. The portrait's body, crossed hands, clothing and landscape are missing, while angular facial construction and flat tones lose its likeness, volume and subtle expression.

Score breakdown

CategoryGPT-6.1 TerraQwen3.5-9B
Task & likeness5.5/100.0/10
Anatomy & construction6.5/100.5/10
Space & placement4.5/100.0/10
Light & reflections6.5/100.0/10
Purposeful detail6.0/100.5/10
Artistry & character6.0/101.0/10
Materials & effects6.0/100.0/10
Visual integrity6.5/100.5/10

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

GPT-6.1 Terra

A coherent sunset illustration with clear prompt fulfillment, controlled framing and varied, purposeful small details. Simplified joints, frontal staging, flattened animal forms and weakly directional shadows limit its anatomical, spatial and physical sophistication.

Qwen3.5-9B

The beach is recognizable, and sweeping shoreline curves provide basic rhythm. Wildlife and playful activity remain poorly resolved, with ambiguous body construction and object contact. The sun glows without corresponding reflections or surface lighting. Fragmented subjects and an unintegrated rectangular panel substantially weaken composition and finish.

Score breakdown

CategoryGPT-6.1 TerraQwen3.5-9B
Task & likeness8.5/101.5/10
Anatomy & construction7.5/100.5/10
Space & placement6.5/101.5/10
Light & reflections5.5/101.0/10
Purposeful detail7.5/102.5/10
Artistry & character7.0/101.5/10
Materials & effects6.5/100.5/10
Visual integrity7.5/101.5/10

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

GPT-6.1 Terra

This benchmark has not been assessed yet.

Qwen3.5-9B

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

A coherent cartoon with expressive animals, readable steering and a clear wake. Fine facial and hull details reward inspection. The main limits are the boatlike craft, simplified joints, weakly braced frontal raccoon and minimal directional lighting or material depth.

Qwen3.5-9B

Bright colors, clean individual shapes and basic animal cues make the scene partly recognizable. Back seating, body continuity, steering and jet ski construction remain unresolved. Background gradients and wave rhythm provide some finish, but substantial anatomical, spatial and interaction weaknesses dominate.

Score breakdown

CategoryGPT-6.1 TerraQwen3.5-9B
Task & likeness6.5/102.5/10
Anatomy & construction5.5/101.0/10
Space & placement6.0/102.0/10
Light & reflections5.0/101.0/10
Purposeful detail7.0/101.5/10
Artistry & character6.0/101.0/10
Materials & effects6.0/101.0/10
Visual integrity7.0/102.5/10

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

A coherent pelican cyclist with expressive proportions, purposeful feather detail and developed bicycle machinery. Continuous body contours, aligned wheels and readable pedal contacts support the scene. Simplified articulation, shallow modelling and an unresolved steering connection limit construction and placement.

Qwen3.5-9B

The oversized bill and orderly spoked wheels make the subject partly recognizable. Clean contours and strong color contrast provide graphic clarity, but unresolved appendages, steering, drivetrain and support dominate the construction. Sparse shading and detail further limit the illustration.

Score breakdown

CategoryGPT-6.1 TerraQwen3.5-9B
Task & likeness7.0/104.0/10
Anatomy & construction7.0/101.5/10
Space & placement6.0/103.0/10
Light & reflections5.5/101.5/10
Purposeful detail7.0/102.5/10
Artistry & character6.5/101.5/10
Materials & effects5.5/101.5/10
Visual integrity6.0/102.5/10

Benchmark task

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