ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Fugu Max vs Gemini 4 Argon vs Qwen3.8 2.4T A95B

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

Price in rating: Included · Exclude price

  1. Sakana AI

    Fugu Max

    Released Sep 11, 2026

    47/100
    • ECI—
    • Price$2.00 / $6.00
    • Context1M
  2. Google

    Gemini 4 Argon

    Released Oct 13, 2026New

    53/100
    • ECI166.6
    • Price$2.00 / $10.00
    • Context1.05M
  3. Alibaba (Qwen)

    Qwen3.8 2.4T A95B

    Released Aug 12, 2026

    32/100
    • 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 (Gemini 4 Argon 53/100, Fugu Max 47/100, Qwen3.8 2.4T A95B 32/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceFugu Max and Qwen3.8 2.4T A95BFugu Max $3.00 · Qwen3.8 2.4T A95B $3.00 · Gemini 4 Argon $4.00 per 1M tokens (3:1 blend)
  • Longest contextGemini 4 ArgonGemini 4 Argon 1,048,576 · Fugu Max 1,000,000 · Qwen3.8 2.4T A95B 262,144 tokens
  • Widest inputsGemini 4 ArgonFugu Max: Text, Images, PDFs · Gemini 4 Argon: Text, Images, PDFs, Audio, Video · Qwen3.8 2.4T A95B: Text
  • Self-hostingQwen3.8 2.4T A95BPublishes downloadable weights (qwen3.8-max)
How the score is built
MeasureWeightFugu MaxGemini 4 ArgonQwen3.8 2.4T A95B
Price50%262026
Inputs & features30%7010035
Context window20%646543
Specs & price only100%47/10053/10032/100

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 Gemini 4 Argon vs Qwen3.8 2.4T A95B specifications side by side
SpecificationFugu MaxSakana AIGemini 4 ArgonGoogleQwen3.8 2.4T A95BAlibaba (Qwen)
Capability
Capabilities Index (ECI)—166.6—
ECI rank—#10 of 158—
GPQA DiamondGraduate-level science questions—96.4%—
FrontierMath Tiers 1–3Research-level mathematics—86.0%—
OTIS Mock AIME 2024–2025Competition mathematics—100%—
SimpleQA VerifiedShort factual questions—76.0%—
Price per million tokens
Input$2.00$2.00$2.00
Output$6.00 (best)$10.00$6.00 (best)
Cached input—$0.10—
Blended (3:1)$3.00 (best)$4.00$3.00 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 9 providersOfficial Google APIMedian of 26 providers
Limits
Context window1,000,000 tokens1,048,576 tokens (best)262,144 tokens
Max output128,000 tokens65,536 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesYesNo
AudioNoYesNo
VideoNoYesNo
ReasoningYesYeslow · medium · highYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsProprietaryProprietaryOpenqwen3.8-max
API model ID—gemini-4-argon—
API providers932 (best)26
ReleasedSep 11, 2026Oct 13, 2026Aug 12, 2026
Knowledge cutoff—Mar 2026—
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
  • Gemini 4 Argon$40.00
  • Qwen3.8 2.4T A95B$32.00
04 — Questions

Which should you choose?

Which is better: Fugu Max, Gemini 4 Argon or Qwen3.8 2.4T A95B?

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 4 Argon 53/100, Fugu Max 47/100, Qwen3.8 2.4T A95B 32/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Fugu Max, Gemini 4 Argon or Qwen3.8 2.4T A95B?

Fugu Max is cheaper at $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); Gemini 4 Argon costs $2.00 input / $10.00 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $3.00 per million tokens for Fugu Max versus $3.00 for Qwen3.8 2.4T A95B (1× as much) and $4.00 for Gemini 4 Argon (1.3× 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, Gemini 4 Argon has an ECI of 166.6 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, Gemini 4 Argon 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?

Gemini 4 Argon has the largest context window at 1,048,576 tokens, against 1,000,000 for Fugu Max and 262,144 for Qwen3.8 2.4T A95B. Maximum output per response: Fugu Max up to 128,000, Gemini 4 Argon up to 65,536, 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; Gemini 4 Argon accepts text, images, PDFs, audio and video; Qwen3.8 2.4T A95B accepts text. Gemini 4 Argon 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 Gemini 4 Argon is proprietary.

Which is newer?

Gemini 4 Argon is the newest, released Oct 13, 2026. Fugu Max came out Sep 11, 2026; Qwen3.8 2.4T A95B came out Aug 12, 2026. Knowledge cutoff: Gemini 4 Argon Mar 2026.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.