stealthmodels.

MODEL BENCHMARKS

Qwen3.8-Max-0902: Pelican

A dated Qwen Max snapshot with a million-token-class context, suited to applications that need an explicit model version.

DATASHEET

Qwen3.8-Max-0902 specs and pricing

A good fit forLong-context reasoning and agent workloads where a pinned snapshot makes evaluation and deployment easier to reproduce.

Qwen3.8-Max-0902Other modelsMedian

PriceDeveloper API, input / output per 1M tokens
$1.65 / $4.951Cheaper than 15 of 46 others
Context windowTokens in one request
1,000,000Larger than 7 of 49 others
Output speedTokens per second, our measurement
76 tokens/sFaster than 8 of 51 others
Developer
Qwen / Alibaba Cloud
Released
2 Sep 2026
Family
Qwen 3.8
Open model
No
Local model
No
Origin
China
Parameters
2.4TEstimated
Active parameters
95BEstimated
Max output
131,072 tokensEstimated
Input → output
Text, image → text
API model ID
qwen3.8-max-0902
Architecture
Mixture-of-Experts; hosted version based on the open Qwen3.8-2.4T-A95BEstimated
All prices and providers2

Alibaba Cloud Model Studio; input 1.65 USD/1M; output 4.951/1M; Documented 0-1M context tier; regional/tiered prices may differ.

  • OpenRouterObserved 2026-10-23
    Input $2Output $6Cached read $0.25

    per 1M tokens

    qwen/qwen3.8-max-0902
  • Alibaba Cloud Model StudioObserved 2026-10-06
    Input $1.65Output $4.951

    per 1M tokens

    Available

    qwen3.8-max-0902
Measurements and sources7

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.