STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemini 3.8 Flash vs Step 5 Preview

Gemini 3.8 Flash leads Step 5 Preview by 8.9 points on StealthMark, 47.9 to 39.0. It leads on 7 of 9 benchmarks, including both games, and Step 5 Preview on 2. Gemini 3.8 Flash scores higher on Beach, with its largest category advantage in anatomy & construction.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

47.9/100Overall rank 20/53
39.0/100Overall rank 36/53

General Intelligence

43.9/100
37.1/100

Visual Intelligence

55.2/100
41.9/100

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

BENCHMARK BY BENCHMARK

Where each model leads

  • Gemini 3.8 Flash
  • Step 5 Preview
  • Other models
  • Median

DATASHEET

Specs and pricing

Both take about 1M tokens of context.

  • Gemini 3.8 Flash
  • Step 5 Preview
  • Other models
  • Median
PricePer 1M output tokens, input below
Gemini 3.8 Flash: $3.75$0.75 inputStep 5 Preview: No list price
Context windowTokens per request, max output below
Gemini 3.8 Flash: 1MTied64K max outputStep 5 Preview: 1MTied
Output speedTokens per second, our measurement
Gemini 3.8 Flash: 170tokens/sStep 5 Preview: Not measured
SizeTotal and active parameters
Gemini 3.8 Flash: Not disclosedStep 5 Preview: 600B27B active
Developer
GoogleStepFun
Released
2 Sep 2026Not published
Origin
United StatesNot published
Input → output
Text, image, video, audio, PDF → textText, image, video → text
Architecture
Not publishedSparse mixture-of-experts; 92 layers (88 MoE), 352 routed experts with 8 selected per token plus a shared expert; grouped-query attention with 512-token sliding windows and full attention every fourth layer; 3 multi-token-prediction layers; vision tower for image and video input

Full datasheets, every price and sourceGemini 3.8 Flash ↗Step 5 Preview ↗

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.

Gemini 3.8 Flash 45.4/100Rank 21/49

Survived 1 of 3
Foresight: complete playing field
Level 311 ptsTurn 17 / 20

Step 5 Preview 59.9/100Rank 42/491 of 3 levels

1 of 3 played
Foresight: complete playing field
Level 122 ptsTurn 28 / 28

Points per level

LevelGemini 3.8 FlashStep 5 Preview
Level 1Second Thoughts
4 ptsOut of lives
22 ptsSurvived
Level 2Pressure Pot
10 ptsSurvived
Pending
Level 3Hide or Flight
11 ptsOut of lives
Pending

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.

Gemini 3.8 Flash 72.9/100Rank 15/50

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

Step 5 Preview 40.7/100Rank 28/50

Cleared 4 of 5
Latch: complete playing field
Level 515 ptsTurn 35 / 40

Points per level

LevelGemini 3.8 FlashStep 5 Preview
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
9 ptsCleared
Level 3Relay vault
18.8 ptsCleared
18.6 ptsCleared
Level 4Passing bay
17.8 ptsClearedFinished early · 1 beacon left
15.6 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
15 ptsFinished early

Newton's Mirror

Same task instructions

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

The judgment

Gemini 3.8 Flash

Crimson is carried well down the camera-facing surface, supporting its earlier interaction. The depiction remains highly simplified, with imperfect material rendering. Isolated wall and floor images and a few highlights provide scant reflective evidence; displaced first reflections, missing receding chains and absent nested sphere and emitter imagery leave the room's optical structure largely unsupported.

Step 5 Preview

The main sphere, airborne black and small colored features occupy broadly appropriate positions. Most of the defining mirror system is absent, and paint interaction remains only partially supported. The small paint features do not visibly establish a separate volume-scale violation.

Score breakdown

CategoryGemini 3.8 FlashStep 5 Preview
State at 600 ms22.5/2520.0/25
Camera and placement11.0/1513.5/15
Reflections4.5/12020.0/120
Materials and scale7.0/107.0/10
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

Gemini 3.8 Flash

The dominant four-point silhouette, luminous color progression, raised brows and enormous grin closely fulfill the brief. Attached, secondary limbs support the exuberant expression. Clean facial drawing and glossy eyes give strong character, while shallow depth, minimally articulated extremities and visible steps in the outer glow limit refinement.

Step 5 Preview

A charming diagonal climber and warm palette communicate the central idea. Simple rounded construction, crowded limb counting, uncertain footholds and an unattached upper shelf limit its physical coherence. Growth bands and the yarn trail add specificity, but the requested material distinctions and unravelled bootie remain underdeveloped.

Score breakdown

CategoryGemini 3.8 FlashStep 5 Preview
Task & likeness8.0/106.0/10
Anatomy & construction6.0/104.5/10
Space & placement6.5/105.0/10
Light & reflections7.0/105.5/10
Purposeful detail5.0/105.5/10
Artistry & character3.5/105.0/10
Materials & effects5.0/106.0/10
Visual integrity6.5/105.0/10

Benchmark task

Gemini 3.8 Flash

A luminous star-shaped creature tests expressive features, a clear silhouette and smooth colour transitions.

Step 5 Preview

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

Mona Lisa

Same task instructions

Precise visual recall and portrait reconstruction.

The judgment

Gemini 3.8 Flash

The dark clothing, overlapping hands and hazy landscape make the Mona Lisa reference recognizable. Replication is limited by the frontal, elongated face, heavy mouth and chin, and poorly resolved hands, wrists and forearm. Soft shading gives some volume, but muddy transitions, blunt landscape shapes and rigid facial modeling weaken the portrait’s expression and painterly character.

Step 5 Preview

A recognizable, coherent simplification with purposeful facial contours and differentiated fingers. These provide more construction and detail than the broad silhouette alone suggests. The oversized face, frontal seated pose, unresolved wrists and sparse landscape still substantially limit likeness, depth and finish.

Score breakdown

CategoryGemini 3.8 FlashStep 5 Preview
Task & likeness3.0/104.0/10
Anatomy & construction2.0/104.0/10
Space & placement3.5/104.0/10
Light & reflections3.0/103.5/10
Purposeful detail5.0/104.0/10
Artistry & character3.0/104.0/10
Materials & effects5.0/103.0/10
Visual integrity1.0/103.5/10

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

Gemini 3.8 Flash

A vivid purple-and-gold sunset anchors an appealing beach composition with dolphins, birds, a turtle and playful accessories. Palm silhouettes frame the bright reflection effectively. Sparse animal anatomy, wirelike palm foliage, conspicuously regular reflection bands and limited surface texture keep the execution below exceptional.

Step 5 Preview

A recognizable sunset beach with clear warm-cool contrast and playful accessories. Basic animal construction, shallow foreground placement and schematic reflections limit spatial and physical credibility. Sparse descriptive detail and abruptly ended sky bands constrain the finish.

Score breakdown

CategoryGemini 3.8 FlashStep 5 Preview
Task & likeness9.0/104.0/10
Anatomy & construction7.0/103.0/10
Space & placement7.0/103.5/10
Light & reflections8.0/103.5/10
Purposeful detail7.0/103.0/10
Artistry & character7.0/103.0/10
Materials & effects7.0/103.5/10
Visual integrity8.0/104.0/10

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

Gemini 3.8 Flash

This benchmark has not been assessed yet.

Step 5 Preview

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

Gemini 3.8 Flash

Expressive animals, a bold diagonal hull and sweeping spray create an appealing action scene. The raccoon's support on the dog's back is unclear, and the dog lacks a readable paw-to-control grip and connected steering assembly. Clean graphic shapes and lively accessories are stronger than the anatomical construction. Sunset illumination and reflections remain largely decorative.

Step 5 Preview

Recognizable animals, a bright palette and identifying accessories support a basic cartoon. Primitive anatomy, partial seated support, unresolved steering and weak hull-water contact limit the central action. Lighting and spray provide atmosphere without establishing convincing physical depth.

Score breakdown

CategoryGemini 3.8 FlashStep 5 Preview
Task & likeness7.0/104.0/10
Anatomy & construction6.0/104.5/10
Space & placement7.0/103.0/10
Light & reflections6.5/103.5/10
Purposeful detail7.5/104.0/10
Artistry & character7.5/103.5/10
Materials & effects7.5/103.0/10
Visual integrity7.5/103.0/10

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

Same task instructions

Subject construction and spatial relationships.

The judgment

Gemini 3.8 Flash

The pelican’s enormous bill, lively feathers and orange bicycle create a clear, appealing composition. Basket contents, spokes and facial details reward inspection. Both legs connect to the body, but foot-to-pedal placement and wing-to-handlebar contact are ambiguous. Bicycle mechanics and lighting remain schematic, limiting an otherwise polished illustration.

Step 5 Preview

The pelican and bicycle are recognizable, with a pleasant palette and basic diffuse shading. The riding relationship fails physically: the bird is unsupported, the front wheel is unmounted, and pedalling is unresolved. Simple geometric construction and sparse material treatment further limit the drawing.

Score breakdown

CategoryGemini 3.8 FlashStep 5 Preview
Task & likeness9.0/103.0/10
Anatomy & construction7.5/103.0/10
Space & placement7.5/103.0/10
Light & reflections7.0/103.0/10
Purposeful detail8.5/104.0/10
Artistry & character8.0/103.0/10
Materials & effects7.0/103.0/10
Visual integrity8.0/102.0/10

Benchmark task

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