STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Iceman Contributor vs GLM-5.3-Flash

GLM-5.3-Flash leads Iceman Contributor by 29.6 points on StealthMark, 48.8 to 19.2. It leads on 8 of 9 benchmarks, including Foresight, and Iceman Contributor on 1, including Latch. Ox Alpha scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
Model guide ↗
Model guide ↗

Overall StealthMark

19.2/100Overall rank 47/53
48.8/100Overall rank 19/53

General Intelligence

11.7/100
42.2/100

Visual Intelligence

31.0/100
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

  • Iceman Contributor
  • GLM-5.3-Flash
  • Other models
  • Median

DATASHEET

Specs and pricing

GLM-5.3-Flash scores higher on StealthMark and runs 1.9× faster in our speed test.

  • Iceman Contributor
  • GLM-5.3-Flash
  • Other models
  • Median
PricePer 1M output tokens, input below
Iceman Contributor: No list priceGLM-5.3-Flash: $0.50$0.15 input
Context windowTokens per request, max output below
Iceman Contributor: Not publishedGLM-5.3-Flash: 1M131K max output
Output speedTokens per second, our measurement
Iceman Contributor: 46tokens/sGLM-5.3-Flash: 891.9× fastertokens/s
SizeTotal and active parameters
Iceman Contributor: Not disclosedGLM-5.3-Flash: 320B18B active
Developer
Not publishedZ.AI
Released
Not published26 Aug 2026
Input → output
Not publishedText, image → text
Architecture
Not publishedHybrid sparse and linear attention MoE

Full datasheets, every price and sourceGLM-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.

Iceman Contributor 3.2/100Rank 47/47

Survived 0 of 3
Foresight: complete playing field
Level 31 ptsTurn 7 / 20

GLM-5.3-Flash 49.0/100Rank 27/472 of 3 levels

2 of 3 played
Foresight: complete playing field
Level 316 ptsTurn 20 / 20

Points per level

LevelIceman ContributorGLM-5.3-Flash
Level 1Second Thoughts
0 ptsOut of lives
9 ptsOut of lives
Level 2Pressure Pot
3 ptsOut of lives
Pending
Level 3Hide or Flight
1 ptsOut of lives
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.

Iceman Contributor 3.6/100Rank 44/48

Cleared 1 of 5
Latch: complete playing field
Level 55 ptsTurn 25 / 40

GLM-5.3-Flash 4.0/100Rank 48/483 of 5 levels

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

Points per level

LevelIceman ContributorGLM-5.3-Flash
Level 1Hold the door
5.2 ptsCleared
4.4 ptsCleared
Level 2Crossfeed
2.8 ptsFinished early
5.2 ptsFinished early
Level 3Relay vault
2.2 ptsFinished early
0.6 ptsFinished early
Level 4Passing bay
4 ptsFinished early
Pending
Level 5Second thoughts
5 ptsFinished early
Not played

Newton's Mirror

Same task instructions

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

The judgment

Iceman Contributor

The image provides limited evidence through rounded volume, faint wall strips and floor echoes. Its main sphere is small and low, the paint beads do not establish the required interaction history, and most of the defining mirror structure is missing.

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

CategoryIceman ContributorGLM-5.3-Flash
State at 600 ms0.5/2514.0/25
Camera and placement2.5/159.0/15
Reflections7.5/12021.5/120
Materials and scale3.0/103.5/10
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

Iceman Contributor

The crystal crown, cyan eyes and blue faceting communicate an icy fantasy character. Anatomical readability is substantially weaker: the ringed torso, crowded facial construction and fingerless appendages do not resolve the requested childlike crouch or pouncing gesture. Sparse surface detail and shallow shading further limit the result.

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

CategoryIceman ContributorGLM-5.3-Flash
Task & likeness4.0/108.5/10
Anatomy & construction3.0/107.5/10
Space & placement4.0/107.5/10
Light & reflections4.5/108.0/10
Purposeful detail4.0/107.5/10
Artistry & character4.5/107.5/10
Materials & effects4.5/107.5/10
Visual integrity4.0/107.0/10

Benchmark task

Iceman Contributor

Character scenes test expression, anatomy, materials and coherent visual construction.

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

Iceman Contributor

The portrait retains a dark silhouette against an earthy landscape, but replication is weak. The frontal body, elongated facial proportions and undifferentiated hands lose the reference's defining pose and likeness. Basic gradients and layered hills provide some coherence, with little anatomical or painterly detail.

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

CategoryIceman ContributorGLM-5.3-Flash
Task & likeness1.5/104.5/10
Anatomy & construction1.5/104.5/10
Space & placement2.5/106.0/10
Light & reflections2.0/106.0/10
Purposeful detail2.0/105.0/10
Artistry & character2.0/105.0/10
Materials & effects2.0/105.5/10
Visual integrity3.0/104.0/10

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

Iceman Contributor

A coherent sunset beach with recognizable animals, playful details and effective palm framing. Connected silhouettes and layered scenery support modest construction and placement credit. Jointless figures, limited foreshortening and an inadequately separated sun and reflection keep the execution basic despite its attractive color.

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

CategoryIceman ContributorGLM-5.3-Flash
Task & likeness7.0/108.0/10
Anatomy & construction3.5/107.0/10
Space & placement6.0/108.0/10
Light & reflections4.0/108.0/10
Purposeful detail5.5/108.0/10
Artistry & character3.5/108.5/10
Materials & effects4.5/106.5/10
Visual integrity5.0/108.0/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Different task instructions

Physical reasoning, light and visual reconstruction.

The judgment

Iceman Contributor

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

Iceman Contributor

The sunset palette and red hull establish an appealing setting, but the central interaction remains unresolved. Overlapping bodies obscure the dog, supported seating is unclear, and no readable paw-to-control grip demonstrates steering. Simple construction, weak environmental lighting and loosely described spray limit depth and finish.

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

CategoryIceman ContributorGLM-5.3-Flash
Task & likeness2.0/107.0/10
Anatomy & construction3.0/105.0/10
Space & placement3.0/106.0/10
Light & reflections4.0/105.0/10
Purposeful detail3.5/106.5/10
Artistry & character2.5/104.0/10
Materials & effects4.0/106.0/10
Visual integrity2.5/106.0/10

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

Iceman Contributor

A recognizable pelican and bicycle sit within an appealing sunset composition. Feather contours, bill shape and atmospheric colour provide character, but disconnected-looking leg origins, unclear pedal contact and unresolved steering weaken the central riding action. Consistent wheel alignment establishes a side view without resolving the rider's support.

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

CategoryIceman ContributorGLM-5.3-Flash
Task & likeness4.0/108.5/10
Anatomy & construction3.5/107.5/10
Space & placement3.5/107.5/10
Light & reflections5.0/106.5/10
Purposeful detail4.5/107.0/10
Artistry & character3.5/108.0/10
Materials & effects4.0/106.5/10
Visual integrity3.0/108.0/10

Benchmark task

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