STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Beam 1.0 501B A23B vs Gemma 4 31B

Beam 1.0 501B A23B leads Gemma 4 31B by 6.1 points on StealthMark, 31.9 to 25.8. It leads on 7 of 9 benchmarks, including both games, and Gemma 4 31B on 2. 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 ↗
All results ↗

Overall StealthMark

31.9/100Overall rank 42/53
25.8/100Overall rank 44/53

General Intelligence

30.9/100
19.1/100

Visual Intelligence

33.8/100
36.7/100

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
Local modelOpen model · Apache 2.0

BENCHMARK BY BENCHMARK

Where each model leads

  • Beam 1.0 501B A23B
  • Gemma 4 31B
  • Other models
  • Median

DATASHEET

Specs and pricing

Beam 1.0 501B A23B scores higher on StealthMark, takes 4× more context and runs 8.4× faster in our speed test. Gemma 4 31B is 2.5× cheaper per output token.

  • Beam 1.0 501B A23B
  • Gemma 4 31B
  • Other models
  • Median
PricePer 1M output tokens, input below
Beam 1.0 501B A23B: $1$0.25 inputGemma 4 31B: $0.402.5× cheaper$0.14 input
Context windowTokens per request, max output below
Beam 1.0 501B A23B: 1M4× larger128K max outputGemma 4 31B: 256K
Output speedTokens per second, our measurement
Beam 1.0 501B A23B: 9728.4× fastertokens/sGemma 4 31B: 116tokens/s
SizeTotal and active parameters
Beam 1.0 501B A23B: 501B23.4B activeGemma 4 31B: 30.7BAll activeEstimated
Developer
Reflection AIGoogle DeepMind
Released
16 Oct 20262 Apr 2026
Origin
United StatesBoth
Input → output
Text → textText, image → text
Architecture
Sparse mixture-of-experts transformer; 52 layers (3 dense, 49 MoE), 256 experts with 8 selected per token; gated GQA and sliding-window attentionDense multimodal transformer with interleaved sliding-window and global attention

Full datasheets, every price and sourceBeam 1.0 501B A23B ↗Gemma 4 31B ↗

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

Gemma 4 31B 30.2/100Rank 30/47

Survived 0 of 3
Foresight: complete playing field
Level 38 ptsTurn 15 / 20

Points per level

LevelBeam 1.0 501B A23BGemma 4 31B
Level 1Second Thoughts
18 ptsOut of lives
9 ptsOut of lives
Level 2Pressure Pot
9 ptsOut of lives
6 ptsOut of lives
Level 3Hide or Flight
9 ptsSurvived
8 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

Gemma 4 31B 26.6/100Rank 39/484 of 5 levels

4 of 5 played
Latch: complete playing field
Level 42.2 ptsTurn 39 / 40

Points per level

LevelBeam 1.0 501B A23BGemma 4 31B
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.6 ptsCleared
9 ptsCleared
Level 3Relay vault
11.2 ptsFinished early
13.2 ptsFinished early
Level 4Passing bay
3.6 ptsFinished early
2.2 ptsFinished early
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

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.

Gemma 4 31B

The sphere's volume, separate airborne black blob and vertical color ordering are readable. The large, low sphere, plain surrounding planes and absent nested optical imagery leave the central geometric and reflection requirements unsupported. Paint contact and transport remain unresolved. Material credit recognizes the visible convex shading, highlights and distinct surface colors while retaining deductions for the schematic finish and oversized blobs.

Score breakdown

CategoryBeam 1.0 501B A23BGemma 4 31B
State at 600 ms20.5/2511.0/25
Camera and placement11.5/153.0/15
Reflections2.0/1200.0/120
Materials and scale3.0/105.5/10
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

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.

Gemma 4 31B

A clean, appealing luminous mascot with coherent body continuity and a readable jar-hugging pose. Rounded highlights, smooth gradients and balanced framing work well. The teardrop silhouette, modest eyes and nearly even grin only partly satisfy the character brief; sparse jar construction and simple geometry limit sophistication.

Score breakdown

CategoryBeam 1.0 501B A23BGemma 4 31B
Task & likeness4.0/106.0/10
Anatomy & construction3.5/106.0/10
Space & placement5.5/107.5/10
Light & reflections5.5/106.5/10
Purposeful detail4.5/105.5/10
Artistry & character4.0/105.0/10
Materials & effects4.5/106.5/10
Visual integrity7.0/107.5/10

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.

Gemma 4 31B

A small luminous creature proudly holding an empty glass jar tests expression, transparent materials and the balance of character and prop.

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.

Gemma 4 31B

The portrait is recognizable through its silhouette, palette and smile, with clean execution of simple shapes. Replication remains weak: the face and pose differ markedly, hands become fingerless ovals, clothing lacks construction, and the landscape loses its atmospheric detail. Basic gradients provide limited volume.

Score breakdown

CategoryBeam 1.0 501B A23BGemma 4 31B
Task & likeness0.0/103.0/10
Anatomy & construction0.0/104.0/10
Space & placement0.0/104.0/10
Light & reflections0.5/103.5/10
Purposeful detail0.0/102.0/10
Artistry & character0.0/103.5/10
Materials & effects0.0/102.5/10
Visual integrity0.0/105.5/10

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.

Gemma 4 31B

A coherent beach illustration with clean silhouettes, a sweeping shoreline and an effective sunset palette. Requested subjects are recognizable, but primitive animal construction, sparse detail, unsupported palm placement and schematic reflections limit drawing sophistication and physical credibility.

Score breakdown

CategoryBeam 1.0 501B A23BGemma 4 31B
Task & likeness7.0/105.0/10
Anatomy & construction5.0/102.0/10
Space & placement6.0/105.0/10
Light & reflections5.0/102.5/10
Purposeful detail5.5/102.0/10
Artistry & character4.0/102.0/10
Materials & effects5.0/102.0/10
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.

Gemma 4 31B

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.

Gemma 4 31B

Clean, simple silhouettes communicate a raccoon riding on a dog. Limited animal specificity, absent steering controls and a flat platform weaken the requested scene. Small facial marks provide purposeful detail, while unresolved support, flat lighting and schematic water restrict physical coherence. Primitive but coherent construction supports basic drawing quality.

Score breakdown

CategoryBeam 1.0 501B A23BGemma 4 31B
Task & likeness5.0/102.5/10
Anatomy & construction3.5/103.0/10
Space & placement5.5/104.0/10
Light & reflections4.0/101.0/10
Purposeful detail6.5/102.5/10
Artistry & character3.5/102.5/10
Materials & effects5.0/102.0/10
Visual integrity6.5/107.0/10

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

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.

Gemma 4 31B

A clean, readable illustration with balanced placement and coherent basic geometry. The sky gradient and ground shadow establish diffuse illumination. Primitive shapes and sparse detail limit artistry, while unclear leg attachment, missing pedal contact and unresolved steering weaken the riding action.

Score breakdown

CategoryBeam 1.0 501B A23BGemma 4 31B
Task & likeness5.5/104.0/10
Anatomy & construction4.5/103.0/10
Space & placement5.0/104.5/10
Light & reflections4.0/105.0/10
Purposeful detail4.0/103.0/10
Artistry & character4.0/103.0/10
Materials & effects4.0/104.0/10
Visual integrity5.5/104.5/10

Benchmark task

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