ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Fugu Max vs Qwen3.7 Flash vs Qwen3.8 2.4T A95B

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)

    Qwen3.7 Flash

    Released Jul 15, 2026

    74/100
    • ECI—
    • Price$0.03 / $0.13
    • Context1M
  3. Alibaba (Qwen)

    Qwen3.8 2.4T A95B

    Released Aug 12, 2026

    38/100
    • ECI—
    • Price$2.00 / $6.00
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.7 Flash 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 priceQwen3.7 FlashQwen3.7 Flash $0.055 · Fugu Max $3.00 · Qwen3.8 2.4T A95B $3.00 per 1M tokens (3:1 blend)
  • Longest contextFugu Max and Qwen3.7 FlashFugu Max 1,000,000 · Qwen3.7 Flash 1,000,000 · Qwen3.8 2.4T A95B 262,144 tokens
  • Widest inputsFugu Max and Qwen3.7 FlashFugu Max: Text, Images, PDFs · Qwen3.7 Flash: Text, Images, Video · Qwen3.8 2.4T A95B: Text
  • Self-hostingQwen3.8 2.4T A95BPublishes downloadable weights (qwen3.8-max)
How the score is built
MeasureWeightFugu MaxQwen3.7 FlashQwen3.8 2.4T A95B
Inputs & features60%708035
Context window40%646443
Specs only100%68/10074/10038/100

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 Qwen3.7 Flash vs Qwen3.8 2.4T A95B specifications side by side
SpecificationFugu MaxSakana AIQwen3.7 FlashAlibaba (Qwen)Qwen3.8 2.4T A95BAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
GPQA DiamondGraduate-level science questions—82.3%—
FrontierMath Tiers 1–3Research-level mathematics—19.3%—
OTIS Mock AIME 2024–2025Competition mathematics—86.7%—
Price per million tokens
Input$2.00$0.03 (best)$2.00
Output$6.00$0.13 (best)$6.00
Cached input—$0.006—
Blended (3:1)$3.00$0.055 (best)$3.00
Long-context rateSame rateOver 32K: $0.10 / $0.40Same rate
Price sourceMedian of 9 providersOfficial Alibaba APIMedian of 26 providers
Limits
Context window1,000,000 tokens (best)1,000,000 tokens (best)262,144 tokens
Max output128,000 tokens131,072 tokens (best)131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesNoNo
AudioNoNoNo
VideoNoYesNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsProprietaryProprietaryOpenqwen3.8-max
API model ID—qwen3.7-flash—
API providers91526 (best)
ReleasedSep 11, 2026Jul 15, 2026Aug 12, 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
  • Qwen3.7 Flash$0.56
  • Qwen3.8 2.4T A95B$32.00
04 — Questions

Which should you choose?

Which is better: Fugu Max, Qwen3.7 Flash or Qwen3.8 2.4T A95B?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.7 Flash 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, Qwen3.7 Flash or Qwen3.8 2.4T A95B?

Qwen3.7 Flash is cheaper at $0.03 input / $0.13 output per million tokens (official Alibaba 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 $0.055 per million tokens for Qwen3.7 Flash versus $3.00 for Fugu Max (55× as much) and $3.00 for Qwen3.8 2.4T A95B (55× 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, Qwen3.7 Flash has not been scored yet and Qwen3.8 2.4T A95B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Fugu Max, Qwen3.7 Flash and Qwen3.8 2.4T A95B 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 Qwen3.7 Flash 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, Qwen3.7 Flash up to 131,072, Qwen3.8 2.4T A95B up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Fugu Max accepts text, images and PDFs; Qwen3.7 Flash accepts text, images and video; Qwen3.8 2.4T A95B accepts text. Fugu Max handles the widest range of inputs.

Are any of these open source?

Qwen3.8 2.4T A95B publishes its weights (qwen3.8-max) and can be self-hosted; Fugu Max and Qwen3.7 Flash is proprietary.

Which is newer?

Fugu Max is the newest, released Sep 11, 2026. Qwen3.8 2.4T A95B came out Aug 12, 2026; Qwen3.7 Flash came out Jul 15, 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.