STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT-6.1 Terra vs GLM-5.3-Flash

GPT-6.1 Terra leads GLM-5.3-Flash by 11.9 points on StealthMark, 60.4 to 48.5. It leads on 5 of 9 benchmarks, including both games, and GLM-5.3-Flash on 4. GPT-6.1 Terra scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

60.4/100Overall rank 9/54
48.5/100Overall rank 20/54

General Intelligence

58.0/100
42.3/100

Visual Intelligence

64.9/100
59.4/100

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 · MIT

BENCHMARK BY BENCHMARK

Where each model leads

  • GPT-6.1 Terra
  • GLM-5.3-Flash
  • Other models
  • Median

DATASHEET

Specs and pricing

GPT-6.1 Terra scores higher on StealthMark. GLM-5.3-Flash is 10× cheaper per output token. Both take about 1.05M tokens of context.

  • GPT-6.1 Terra
  • GLM-5.3-Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
GPT-6.1 Terra: $5$1 inputGLM-5.3-Flash: $0.5010× cheaper$0.15 input
Context windowTokens per request, max output below
GPT-6.1 Terra: 1.05MTied128K max outputGLM-5.3-Flash: 1MTied131K max output
Output speedTokens per second, our measurement
GPT-6.1 Terra: Not measuredGLM-5.3-Flash: 89tokens/s
SizeTotal and active parameters
GPT-6.1 Terra: Not disclosedGLM-5.3-Flash: 320B18B active
Developer
OpenAIZ.AI
Released
26 Oct 202626 Aug 2026
Origin
United StatesNot published
Input → output
Text, image → textBoth
Architecture
Not publishedHybrid sparse and linear attention MoE

Full datasheets, every price and sourceGPT-6.1 Terra ↗GLM-5.3-Flash ↗

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

GLM-5.3-Flash 47.0/100Rank 21/50

Survived 1 of 3
Foresight: complete playing field
Level 316 ptsTurn 20 / 20

Points per level

LevelGPT-6.1 TerraGLM-5.3-Flash
Level 1Second Thoughts
21 ptsSurvived
9 ptsOut of lives
Level 2Pressure Pot
9 ptsOut of lives
6 ptsOut of lives
Level 3Hide or Flight
15 ptsSurvived
16 ptsSurvived

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

GLM-5.3-Flash 4.0/100Rank 51/513 of 5 levels

3 of 5 played
Latch: complete playing field
Level 30.6 ptsTurn 33 / 36

Points per level

LevelGPT-6.1 TerraGLM-5.3-Flash
Level 1Hold the door
5.2 ptsCleared
4.4 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
5.2 ptsFinished early
Level 3Relay vault
19.2 ptsCleared
0.6 ptsFinished early
Level 4Passing bay
17.8 ptsClearedFinished early · 3 beacons left
Pending
Level 5Second thoughts
20.6 ptsCleared
Not played

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.

GLM-5.3-Flash

The setup is recognizable, but the paint interaction remains poorly established and off-center. The first wall and floor images provide coherent placement, scale, silhouette and occlusion cues, with faint lower echoes. Missing receding chains, nested imagery and ordered emitter mappings leave the reflection system heavily simplified. Dull shading does not convincingly depict polished steel or mirrors.

Score breakdown

CategoryGPT-6.1 TerraGLM-5.3-Flash
State at 600 ms23.0/2514.0/25
Camera and placement11.0/159.0/15
Reflections33.0/12021.5/120
Materials and scale7.5/103.5/10
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

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.

GLM-5.3-Flash

The expressive emerald face, ivory horns, gold accents and fine veining closely match the brief. Rounded volumes and layered shading create an appealing mascot. Rear hoof placement is cramped, lighting is somewhat inconsistent, and conspicuous white patches behind the muzzle interrupt the finish. Surfaces remain visibly stylized rather than photographic.

Score breakdown

CategoryGPT-6.1 TerraGLM-5.3-Flash
Task & likeness7.5/108.5/10
Anatomy & construction6.5/107.5/10
Space & placement6.5/107.5/10
Light & reflections6.0/108.0/10
Purposeful detail6.5/107.5/10
Artistry & character6.5/107.5/10
Materials & effects6.0/107.5/10
Visual integrity6.0/107.0/10

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.

GLM-5.3-Flash

A rounded jade bull raising a hoof tests anatomy, balance and the appearance of polished stone and metal.

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.

GLM-5.3-Flash

The crossed arms, green dress and hazy landscape clearly evoke Mona Lisa. Replication is limited by the frontal pose, oversized eyes, elongated face and pronounced lips. Overlapping finger strips lack convincing knuckles and palm volume. The balanced framing and soft shading provide cohesion, but simplified anatomy, repetitive folds and blurred scenery keep the portrait basic.

Score breakdown

CategoryGPT-6.1 TerraGLM-5.3-Flash
Task & likeness5.5/104.5/10
Anatomy & construction6.5/104.5/10
Space & placement4.5/106.0/10
Light & reflections6.5/106.0/10
Purposeful detail6.0/105.0/10
Artistry & character6.0/105.0/10
Materials & effects6.0/105.5/10
Visual integrity6.5/104.0/10

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

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.

GLM-5.3-Flash

Framing palms, a vivid sunset palette and balanced kite and umbrella create an appealing beach illustration. Layered water and shoreline give the scene depth, while aligned reflections reinforce the sunset. Small accessories add character and reward inspection. Figures and animals remain schematic, some overlaps are difficult to read, and simplified shadows and flat surfaces limit physical richness.

Score breakdown

CategoryGPT-6.1 TerraGLM-5.3-Flash
Task & likeness8.5/108.0/10
Anatomy & construction7.5/107.0/10
Space & placement6.5/108.0/10
Light & reflections5.5/108.0/10
Purposeful detail7.5/108.0/10
Artistry & character7.0/108.5/10
Materials & effects6.5/106.5/10
Visual integrity7.5/108.0/10

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

This benchmark has not been assessed yet.

GLM-5.3-Flash

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

Different 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.

GLM-5.3-Flash

Recognizable animals, a supported riding pose and an energetic diagonal composition make the scene readable. Character details and spray strengthen its appeal. Simple limb construction, limited directional lighting and an unresolved steering connection constrain the drawing's physical precision and complexity.

Score breakdown

CategoryGPT-6.1 TerraGLM-5.3-Flash
Task & likeness6.5/107.0/10
Anatomy & construction5.5/105.0/10
Space & placement6.0/106.0/10
Light & reflections5.0/105.0/10
Purposeful detail7.0/106.5/10
Artistry & character6.0/104.0/10
Materials & effects6.0/106.0/10
Visual integrity7.0/106.0/10

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

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.

GLM-5.3-Flash

The pelican, bicycle and seaside setting form a clear, appealing illustration. Circular wheels, readable frame tubes and clean silhouettes support the action. The legs connect to the body, but the far foot's pedal contact and wing-to-handlebar junction are cramped. Simple shading, uniform wave marks and limited surface texture keep the rendering relatively flat.

Score breakdown

CategoryGPT-6.1 TerraGLM-5.3-Flash
Task & likeness7.0/108.5/10
Anatomy & construction7.0/107.5/10
Space & placement6.0/107.5/10
Light & reflections5.5/106.5/10
Purposeful detail7.0/107.0/10
Artistry & character6.5/108.0/10
Materials & effects5.5/106.5/10
Visual integrity6.0/108.0/10

Benchmark task

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