STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemini 3.8 Flash vs GPT-6.1 Terra

GPT-6.1 Terra leads Gemini 3.8 Flash by 12.5 points on StealthMark, 60.4 to 47.9. It leads on 6 of 9 benchmarks, including both games, and Gemini 3.8 Flash on 3. GPT-6.1 Terra scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

47.9/100Overall rank 21/54
60.4/100Overall rank 9/54

General Intelligence

43.9/100
58.0/100

Visual Intelligence

55.2/100
64.9/100

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
  • GPT-6.1 Terra
  • Other models
  • Median

DATASHEET

Specs and pricing

Gemini 3.8 Flash is 33% cheaper per output token. GPT-6.1 Terra scores higher on StealthMark. Both take about 1M tokens of context.

  • Gemini 3.8 Flash
  • GPT-6.1 Terra
  • Other models
  • Median
PricePer 1M output tokens, input below
Gemini 3.8 Flash: $3.7533% cheaper$0.75 inputGPT-6.1 Terra: $5$1 input
Context windowTokens per request, max output below
Gemini 3.8 Flash: 1MTied64K max outputGPT-6.1 Terra: 1.05MTied128K max output
Output speedTokens per second, our measurement
Gemini 3.8 Flash: 170tokens/sGPT-6.1 Terra: Not measured
Developer
GoogleOpenAI
Released
2 Sep 202626 Oct 2026
Origin
United StatesBoth
Input → output
Text, image, video, audio, PDF → textText, image → text

Full datasheets, every price and sourceGemini 3.8 Flash ↗GPT-6.1 Terra ↗

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 22/50

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

GPT-6.1 Terra 62.0/100Rank 9/50

Survived 2 of 3
Foresight: complete playing field
Level 315 ptsTurn 20 / 20

Points per level

LevelGemini 3.8 FlashGPT-6.1 Terra
Level 1Second Thoughts
4 ptsOut of lives
21 ptsSurvived
Level 2Pressure Pot
10 ptsSurvived
9 ptsOut of lives
Level 3Hide or Flight
11 ptsOut of lives
15 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.

Gemini 3.8 Flash 72.9/100Rank 16/51

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

GPT-6.1 Terra 77.7/100Rank 12/51

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

Points per level

LevelGemini 3.8 FlashGPT-6.1 Terra
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
9.8 ptsCleared
Level 3Relay vault
18.8 ptsCleared
19.2 ptsCleared
Level 4Passing bay
17.8 ptsClearedFinished early · 1 beacon left
17.8 ptsClearedFinished early · 3 beacons left
Level 5Second thoughts
20.6 ptsCleared
20.6 ptsCleared

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.

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.

Score breakdown

CategoryGemini 3.8 FlashGPT-6.1 Terra
State at 600 ms22.5/2523.0/25
Camera and placement11.0/1511.0/15
Reflections4.5/12033.0/120
Materials and scale7.0/107.5/10
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

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.

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.

Score breakdown

CategoryGemini 3.8 FlashGPT-6.1 Terra
Task & likeness8.0/107.5/10
Anatomy & construction6.0/106.5/10
Space & placement6.5/106.5/10
Light & reflections7.0/106.0/10
Purposeful detail5.0/106.5/10
Artistry & character3.5/106.5/10
Materials & effects5.0/106.0/10
Visual integrity6.5/106.0/10

Benchmark task

Gemini 3.8 Flash

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

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.

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.

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.

Score breakdown

CategoryGemini 3.8 FlashGPT-6.1 Terra
Task & likeness3.0/105.5/10
Anatomy & construction2.0/106.5/10
Space & placement3.5/104.5/10
Light & reflections3.0/106.5/10
Purposeful detail5.0/106.0/10
Artistry & character3.0/106.0/10
Materials & effects5.0/106.0/10
Visual integrity1.0/106.5/10

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.

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.

Score breakdown

CategoryGemini 3.8 FlashGPT-6.1 Terra
Task & likeness9.0/108.5/10
Anatomy & construction7.0/107.5/10
Space & placement7.0/106.5/10
Light & reflections8.0/105.5/10
Purposeful detail7.0/107.5/10
Artistry & character7.0/107.0/10
Materials & effects7.0/106.5/10
Visual integrity8.0/107.5/10

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.

GPT-6.1 Terra

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.

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.

Score breakdown

CategoryGemini 3.8 FlashGPT-6.1 Terra
Task & likeness7.0/106.5/10
Anatomy & construction6.0/105.5/10
Space & placement7.0/106.0/10
Light & reflections6.5/105.0/10
Purposeful detail7.5/107.0/10
Artistry & character7.5/106.0/10
Materials & effects7.5/106.0/10
Visual integrity7.5/107.0/10

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

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.

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.

Score breakdown

CategoryGemini 3.8 FlashGPT-6.1 Terra
Task & likeness9.0/107.0/10
Anatomy & construction7.5/107.0/10
Space & placement7.5/106.0/10
Light & reflections7.0/105.5/10
Purposeful detail8.5/107.0/10
Artistry & character8.0/106.5/10
Materials & effects7.0/105.5/10
Visual integrity8.0/106.0/10

Benchmark task

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