STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Beam 1.0 501B A23B vs Glyph Cluster

Beam 1.0 501B A23B leads Glyph Cluster by 13.0 points on StealthMark, 31.9 to 18.9. It leads on 8 of 9 benchmarks, including both games, and Glyph Cluster on 1. Beam 1.0 501B A23B scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

31.9/100Overall rank 42/53
18.9/100Overall rank 48/53

General Intelligence

30.9/100
12.0/100

Visual Intelligence

33.8/100
29.8/100

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

Open modelApache 2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Beam 1.0 501B A23B
  • Glyph Cluster
  • Other models
  • Median

DATASHEET

Specs and pricing

Beam 1.0 501B A23B scores higher on StealthMark and runs 14× faster in our speed test.

  • Beam 1.0 501B A23B
  • Glyph Cluster
  • Other models
  • Median
PricePer 1M output tokens, input below
Beam 1.0 501B A23B: $1$0.25 inputGlyph Cluster: No list price
Context windowTokens per request, max output below
Beam 1.0 501B A23B: 1M128K max outputGlyph Cluster: Not published
Output speedTokens per second, our measurement
Beam 1.0 501B A23B: 97214× fastertokens/sGlyph Cluster: 69tokens/s
SizeTotal and active parameters
Beam 1.0 501B A23B: 501B23.4B activeGlyph Cluster: Not disclosed
Developer
Reflection AINot published
Released
16 Oct 2026Not published
Origin
United StatesNot published
Input → output
Text → textNot published
Architecture
Sparse mixture-of-experts transformer; 52 layers (3 dense, 49 MoE), 256 experts with 8 selected per token; gated GQA and sliding-window attentionNot published

Full datasheets, every price and sourceBeam 1.0 501B A23B ↗

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.

Beam 1.0 501B A23B 49.4/100Rank 18/47

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

Glyph Cluster 6.4/100Rank 44/47

Survived 0 of 3
Foresight: complete playing field
Level 33 ptsTurn 5 / 20

Points per level

LevelBeam 1.0 501B A23BGlyph Cluster
Level 1Second Thoughts
18 ptsOut of lives
3 ptsOut of lives
Level 2Pressure Pot
9 ptsOut of lives
3 ptsOut of lives
Level 3Hide or Flight
9 ptsSurvived
3 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.

Beam 1.0 501B A23B 37.3/100Rank 29/48

Cleared 2 of 5
Latch: complete playing field
Level 55 ptsTurn 30 / 40

Glyph Cluster 3.6/100Rank 44/48

Cleared 1 of 5
Latch: complete playing field
Level 59 ptsTurn 25 / 40

Points per level

LevelBeam 1.0 501B A23BGlyph Cluster
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
2 ptsOut of turns
Level 3Relay vault
11.2 ptsFinished early
4.2 ptsFinished early
Level 4Passing bay
3.6 ptsFinished early
1 ptsOut of turns
Level 5Second thoughts
5 ptsFinished early
9 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

Beam 1.0 501B A23B

Central object placement is fairly close, but the defining mirrored-room structure is missing. The paint colors suggest the required contact order without establishing their different interaction histories. The faint floor oval does not demonstrate valid reflection geometry, so it earns no reflection credit. Rounded volume and glossy paint provide limited material credit despite weak metallic finishes and oversized paint bodies.

Glyph Cluster

Rounded sphere volume, compact colored forms and crimson-below-cyan ordering provide limited agreement. The visible paint does not establish the required interaction history, the sphere and black blob are displaced from the prescribed projection, and most of the defining mirror-room structure is missing or unresolved. The faint reflection echoes earn limited optical credit.

Score breakdown

CategoryBeam 1.0 501B A23BGlyph Cluster
State at 600 ms20.5/255.0/25
Camera and placement11.5/153.0/15
Reflections2.0/1208.0/120
Materials and scale3.0/103.0/10
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

Beam 1.0 501B A23B

An appealing expression and warm palette support a coherent simple cartoon. The central polishing joke is not legible: the cloth is unresolved and the nose sits away from the fan. Pointed radial plates, uncertain limb attachments and weak ground contact limit construction, while restrained surface detail limits material richness.

Glyph Cluster

A charming palette and three expressive companions make the concept recognizable. The dominant paper enclosure overwhelms the small group, the plum character lacks a clear brace silhouette, and the cuddle remains difficult to trace. Sparse furnishings, ambiguous folds and generalized shading limit the promised lived-in richness and tactile depth.

Score breakdown

CategoryBeam 1.0 501B A23BGlyph Cluster
Task & likeness4.0/103.5/10
Anatomy & construction3.5/102.5/10
Space & placement5.5/104.0/10
Light & reflections5.5/103.5/10
Purposeful detail4.5/104.5/10
Artistry & character4.0/103.0/10
Materials & effects4.5/102.0/10
Visual integrity7.0/103.0/10

Benchmark task

Beam 1.0 501B A23B

A golden pangolin polishes its oversized amber tail while its nose smudges the same scale. The scene tests expressive anatomy, physical contact and contrasting translucent, polished and soft materials.

Glyph Cluster

Punctuation-shaped companions gather inside a curled paper home. The scene tests expressive silhouettes, close interaction and the coherence of a detailed miniature environment.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Beam 1.0 501B A23B

The candidate shows a faint warm oval against an almost entirely black field. Minimal placement and smooth tonal variation are visible, but the portrait, anatomy, crossed hands and landscape remain unreadable. The saved comparisons provide no specific evidence supporting a change to the baseline categories.

Glyph Cluster

The portrait has a continuous body silhouette, attached sleeves and hands, and simple landscape depth. Its oversized pale head enclosure nearly erases the expression, while separated fists, ochre clothing and frontal construction weaken Mona Lisa likeness. Sparse detail, flat materials and ambiguous facial layers leave the drawing seriously unresolved.

Score breakdown

CategoryBeam 1.0 501B A23BGlyph Cluster
Task & likeness0.0/102.0/10
Anatomy & construction0.0/100.5/10
Space & placement0.0/102.0/10
Light & reflections0.5/101.0/10
Purposeful detail0.0/101.0/10
Artistry & character0.0/100.5/10
Materials & effects0.0/101.0/10
Visual integrity0.0/103.0/10

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

Beam 1.0 501B A23B

A coherent, cheerful beach illustration fulfills the main subjects with clean shapes and a strong sunset focal point. Its basic geometric construction, ambiguous animal anatomy, shallow depth and schematic lighting limit its accomplishment. Decorative details provide interest without developing intricate forms or convincing physical surfaces.

Glyph Cluster

A cheerful, recognizable beach illustration with playful accessories and mostly clean silhouettes. Sunset colors and soft glow supply atmosphere, but abbreviated anatomy, unexplained airborne animals, weak ground contact and absent water reflections limit physical coherence. Small details add interest without consistently resolving construction or materials.

Score breakdown

CategoryBeam 1.0 501B A23BGlyph Cluster
Task & likeness7.0/106.0/10
Anatomy & construction5.0/104.0/10
Space & placement6.0/105.0/10
Light & reflections5.0/104.0/10
Purposeful detail5.5/105.5/10
Artistry & character4.0/104.0/10
Materials & effects5.0/104.0/10
Visual integrity5.0/105.0/10

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

Beam 1.0 501B A23B

This benchmark has not been assessed yet.

Glyph Cluster

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

Beam 1.0 501B A23B

A cheerful, readable illustration with recognizable animals, expressive faces and useful accessories. Simple rounded construction limits complexity, while ambiguous steering attachments and weak hull-to-water contact reduce physical coherence. Lighting and surface effects establish the setting without convincing environmental interaction.

Glyph Cluster

Recognizable animals and clean shapes give the scene charm, but the requested steering action is visibly incomplete. Simplified joints, weak vehicle construction and uncertain water contact limit physical coherence. Flat lighting, sparse functional detail and a small focal group keep the illustration basic despite its tidy edges.

Score breakdown

CategoryBeam 1.0 501B A23BGlyph Cluster
Task & likeness5.0/105.0/10
Anatomy & construction3.5/103.0/10
Space & placement5.5/104.0/10
Light & reflections4.0/102.5/10
Purposeful detail6.5/103.5/10
Artistry & character3.5/103.0/10
Materials & effects5.0/103.0/10
Visual integrity6.5/105.5/10

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

Different task instructions

Subject construction and spatial relationships.

The judgment

Beam 1.0 501B A23B

A cheerful, clearly readable pelican-and-bicycle illustration with clean contours and balanced composition. Simple geometric construction limits artistic complexity, while ambiguous neck and steering overlaps, merged pedal contacts and an incomplete drivetrain weaken physical coherence.

Glyph Cluster

A readable cartoon with open framing, aligned bicycle wheels and modest atmospheric effects. Pelican likeness is approximate, while the narrow neck, crowded feet, absent steering contact and unclear drivetrain weaken the riding action. Clean shapes help presentation, but shallow space and inconsistent shading limit the finish.

Score breakdown

CategoryBeam 1.0 501B A23BGlyph Cluster
Task & likeness5.5/106.0/10
Anatomy & construction4.5/103.0/10
Space & placement5.0/106.0/10
Light & reflections4.0/103.5/10
Purposeful detail4.0/104.0/10
Artistry & character4.0/103.0/10
Materials & effects4.0/104.5/10
Visual integrity5.5/106.0/10

Benchmark task

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