ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Fugu Max vs Qwen3.8 2.4T A95B vs Step 5 Preview

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. Sakana AI

    Fugu Max

    Released Sep 11, 2026

    68/100
    • ECI—
    • Price$2.00 / $6.00
    • Context1M
  2. Alibaba (Qwen)

    Qwen3.8 2.4T A95B

    Released Aug 12, 2026

    38/100
    • ECI—
    • Price$2.00 / $6.00
    • Context262K
  3. StepFun

    Step 5 Preview

    Released Sep 16, 2026

    74/100
    • ECI—
    • Price$1.00 / $2.70
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Step 5 Preview 74/100, Fugu Max 68/100, Qwen3.8 2.4T A95B 38/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceStep 5 PreviewStep 5 Preview $1.43 · Fugu Max $3.00 · Qwen3.8 2.4T A95B $3.00 per 1M tokens (3:1 blend)
  • Longest contextFugu Max and Step 5 PreviewFugu Max 1,000,000 · Step 5 Preview 1,000,000 · Qwen3.8 2.4T A95B 262,144 tokens
  • Widest inputsFugu Max and Step 5 PreviewFugu Max: Text, Images, PDFs · Qwen3.8 2.4T A95B: Text · Step 5 Preview: Text, Images, Video
  • Self-hostingQwen3.8 2.4T A95B and Step 5 PreviewPublishes downloadable weights (qwen3.8-max)
How the score is built
MeasureWeightFugu MaxQwen3.8 2.4T A95BStep 5 Preview
Inputs & features60%703580
Context window40%644364
Specs only100%68/10038/10074/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Fugu Max vs Qwen3.8 2.4T A95B vs Step 5 Preview specifications side by side
SpecificationFugu MaxSakana AIQwen3.8 2.4T A95BAlibaba (Qwen)Step 5 PreviewStepFun
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$2.00$2.00$1.00 (best)
Output$6.00$6.00$2.70 (best)
Cached input——$0.10
Blended (3:1)$3.00$3.00$1.43 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 9 providersMedian of 26 providersOfficial StepFun (Global) API
Limits
Context window1,000,000 tokens (best)262,144 tokens1,000,000 tokens (best)
Max output128,000 tokens131,072 tokens1,000,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesYeslow · medium · high
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsProprietaryOpenqwen3.8-maxOpen
API model ID——step-5-preview
API providers926 (best)21
ReleasedSep 11, 2026Aug 12, 2026Sep 16, 2026
Knowledge cutoff———
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Fugu Max$32.00
  • Qwen3.8 2.4T A95B$32.00
  • Step 5 Preview$15.40
04 — Questions

Which should you choose?

Which is better: Fugu Max, Qwen3.8 2.4T A95B or Step 5 Preview?

There is not enough shared capability evidence to name an overall winner. The scores (Step 5 Preview 74/100, Fugu Max 68/100, Qwen3.8 2.4T A95B 38/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Fugu Max, Qwen3.8 2.4T A95B or Step 5 Preview?

Step 5 Preview is cheaper at $1.00 input / $2.70 output per million tokens (official StepFun (Global) API price). Fugu Max costs $2.00 input / $6.00 output per million tokens (median across 9 API providers); Qwen3.8 2.4T A95B costs $2.00 input / $6.00 output per million tokens (median across 26 API providers). At a typical mix of three input tokens to one output token, that is $1.43 per million tokens for Step 5 Preview versus $3.00 for Fugu Max (2.1× as much) and $3.00 for Qwen3.8 2.4T A95B (2.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Fugu Max has not been scored yet, Qwen3.8 2.4T A95B has not been scored yet and Step 5 Preview has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Fugu Max, Qwen3.8 2.4T A95B and Step 5 Preview yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Fugu Max and Step 5 Preview have the largest context windows (1,000,000 and 1,000,000 tokens), against 262,144 for Qwen3.8 2.4T A95B. Maximum output per response: Fugu Max up to 128,000, Qwen3.8 2.4T A95B up to 131,072, Step 5 Preview up to 1,000,000 tokens.

Which can read images, PDFs, audio or video?

Fugu Max accepts text, images and PDFs; Qwen3.8 2.4T A95B accepts text; Step 5 Preview accepts text, images and video. Fugu Max handles the widest range of inputs.

Are any of these open source?

Qwen3.8 2.4T A95B and Step 5 Preview publishes its weights (qwen3.8-max) and can be self-hosted; Fugu Max is proprietary.

Which is newer?

Step 5 Preview is the newest, released Sep 16, 2026. Fugu Max came out Sep 11, 2026; Qwen3.8 2.4T A95B came out Aug 12, 2026.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.