stealthmodels.

MODEL BENCHMARKS

Gemini 3.8 Flash

A fast hosted model that accepts text, images, audio and video, with a million-token-class context.

BENCHMARK BY BENCHMARK

Gemini 3.8 Flash benchmark scores

StealthMark
47.9/100Overall rank 26/58
General Intelligence
43.9/100
Visual Intelligence
55.2/100

Gemini 3.8 FlashOther modelsMedian

Reasoning efficiency

How many reasoning tokens a model needs for the quality it delivers.

Single-step reasoningHow much it reasons to understand a taskRank 16/56
Multi-step reasoningHow much it keeps reasoning as a task goes onRank 16/54

Cost efficiency

How much Performance you get for your money.

Rank 18/52

DATASHEET

Gemini 3.8 Flash specs and pricing

A good fit forHigh-volume media analysis and agents that need to work across documents, recordings and video through one API.

Gemini 3.8 FlashOther modelsMedian

PriceDeveloper API, input / output per 1M tokens
$0.75 / $3.75Cheaper than 21 of 46 others
Context windowTokens in one request
1,048,576Joint largest with 21 others
Output speedTokens per second, our measurement
170 tokens/sFaster than 35 of 51 others
Developer
Google
Released
2 Sep 2026
Family
Gemini 3.8
Open model
No
Local model
No
Origin
United States
Parameters
Not disclosed
Max output
65,536 tokens
Input → output
Text, image, video, audio, PDF → text
API model ID
gemini-3.8-flash
All prices and providers2

Gemini Developer API; input 0.75 USD/1M; cached read 0.075/1M; output 3.75/1M; Introductory paid rate through 2026-12-31; published 2027 rates are higher. Free tier is also documented.

  • OpenRouterObserved 2026-10-23
    Input $0.825Output $4.125Cached read $0.0825Cached write $0.04166667

    per 1M tokens

    google/gemini-3.8-flash
  • Gemini Developer APIObserved 2026-10-06
    Input $0.75Output $3.75Cached read $0.075Batch input $0.375Batch output $1.875

    per 1M tokens

    Available

    gemini-3.8-flash
Measurements and sources7

GAME BENCHMARKS

Watch Gemini 3.8 Flash play

Foresight

Anticipating threats and planning ahead

45.4/100Rank 24/54
Survived 1 of 3
Foresight: complete playing field
Level 311 ptsTurn 17 / 20

Points per level

  1. Level 1Second Thoughts4 ptsBest 27Out of lives
  2. Level 2Pressure Pot10 ptsBest 13Survived
  3. Level 3Hide or Flight11 ptsBest 19Out of lives

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.

Latch

Cooperative planning and learning from experience

72.9/100Rank 17/55
Cleared 5 of 5
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

Points per level

  1. Level 1Hold the door5.2 ptsBest 5.2Cleared
  2. Level 2Crossfeed9.8 ptsBest 10.2Cleared
  3. Level 3Relay vault18.8 ptsBest 19.2Cleared
  4. Level 4Passing bay17.8 ptsBest 18.2ClearedFinished early · 1 beacon left
  5. Level 5Second thoughts20.6 ptsBest 20.8Cleared

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 benchmark results ↗

StealthMark score

StealthMark measures how well a model’s abilities carry over to original, demanding tasks it could not have trained for: physical and spatial reasoning, planning across many steps, and precise visual work. How StealthMark works explains every benchmark, what it tests and why it is hard.

General Intelligence

The ability to reason, plan, solve problems and understand how things relate and behave. A high score means it thinks hard problems through, from careful analysis to plans that span many steps.

Visual Intelligence

The ability to understand visual intent and turn ideas, descriptions and plans into coherent, effective visuals. A high score means design ideas come out the way you meant them, in illustrations, icons, diagrams or interface visuals.

Overall score

Overall shows how well a model’s abilities carry over to original, demanding tasks, weighting every benchmark into one score. Estimated means the total includes an estimate for one missing scene.

Judging

Scores reflect how well each result meets the benchmark requirements. Game scores come from the recorded play: the points earned on each level and how each level ended. How StealthMark keeps scores honest.

Games

Each game is a sequence of levels, and earlier moves carry into later levels. A level that was not played is shown as not played and never counts as zero. Play every level of Latch or Foresight yourself to get a score calculated like the models’.

Reasoning efficiency

Good results with little thinking score high. On each task, a model’s result and reasoning tokens are compared with every other model and combined with the Balanced Integration Score (Liesefeld & Janczyk, 2019); 50 is average. Single step shows how much reasoning a model needs to understand and solve one problem, multi-step how efficiently it keeps working on a task by building on its earlier reasoning, as in agentic workflows. Not part of StealthMark.

Cost efficiency

How much StealthMark a model delivers for its money, in StealthMark points per dollar: its overall score divided by what one benchmark task costs it on average. The cost is what our runs were charged, or their tokens at the model’s list price; benchmarks a model has not run yet are estimated from its other costs. Like StealthMark, it is absolute and compares with no other model. Not part of StealthMark.

BENCHMARK RESULTS

Compare results

This link opens the same results in the same order.

StealthMark benchmark results

Reset benchmark preferences?

Return to the default view, clear comparison selections and restore the advertisement.