ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek V3.2 vs Fugu Max vs Qwen3.8 Max 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. DeepSeek

    DeepSeek V3.2

    Released Dec 1, 2025

    34/100
    • ECI146.3
    • Price$0.28 / $0.42
    • Context128K
  2. Sakana AI

    Fugu Max

    Released Sep 11, 2026

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

    Qwen3.8 Max Preview

    Released Jul 19, 2026

    68/100
    • ECI—
    • Price$2.00 / $6.00
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Fugu Max 68/100, Qwen3.8 Max Preview 68/100, DeepSeek V3.2 34/100) 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 priceDeepSeek V3.2DeepSeek V3.2 $0.315 · Fugu Max $3.00 · Qwen3.8 Max Preview $3.00 per 1M tokens (3:1 blend)
  • Longest contextFugu Max and Qwen3.8 Max PreviewFugu Max 1,000,000 · Qwen3.8 Max Preview 1,000,000 · DeepSeek V3.2 128,000 tokens
  • Widest inputsFugu Max and Qwen3.8 Max PreviewDeepSeek V3.2: Text · Fugu Max: Text, Images, PDFs · Qwen3.8 Max Preview: Text, Images, Video
  • Self-hostingDeepSeek V3.2Publishes downloadable weights (MIT License)
How the score is built
MeasureWeightDeepSeek V3.2Fugu MaxQwen3.8 Max Preview
Inputs & features60%357070
Context window40%326464
Specs only100%34/10068/10068/100

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.

DeepSeek V3.2 vs Fugu Max vs Qwen3.8 Max Preview specifications side by side
SpecificationDeepSeek V3.2DeepSeekFugu MaxSakana AIQwen3.8 Max PreviewAlibaba (Qwen)
Capability
Capabilities Index (ECI)146.3——
ECI rank#87 of 158——
GPQA DiamondGraduate-level science questions83.4%——
OTIS Mock AIME 2024–2025Competition mathematics87.8%——
Price per million tokens
Input$0.28 (best)$2.00$2.00
Output$0.42 (best)$6.00$6.00
Cached input———
Blended (3:1)$0.315 (best)$3.00$3.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 30 providersMedian of 9 providersMedian of 6 providers
Limits
Context window128,000 tokens1,000,000 tokens (best)1,000,000 tokens (best)
Max output64,000 tokens128,000 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenMIT LicenseProprietaryProprietary
API model ID———
API providers30 (best)96
ReleasedDec 1, 2025Sep 11, 2026Jul 19, 2026
Knowledge cutoffJul 2024——
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.

  • DeepSeek V3.2$3.64
  • Fugu Max$32.00
  • Qwen3.8 Max Preview$32.00
04 — Questions

Which should you choose?

Which is better: DeepSeek V3.2, Fugu Max or Qwen3.8 Max Preview?

There is not enough shared capability evidence to name an overall winner. The scores (Fugu Max 68/100, Qwen3.8 Max Preview 68/100, DeepSeek V3.2 34/100) 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, DeepSeek V3.2, Fugu Max or Qwen3.8 Max Preview?

DeepSeek V3.2 is cheaper at $0.28 input / $0.42 output per million tokens (median across 30 API providers). Fugu Max costs $2.00 input / $6.00 output per million tokens (median across 9 API providers); Qwen3.8 Max Preview costs $2.00 input / $6.00 output per million tokens (median across 6 API providers). At a typical mix of three input tokens to one output token, that is $0.315 per million tokens for DeepSeek V3.2 versus $3.00 for Fugu Max (9.5× as much) and $3.00 for Qwen3.8 Max Preview (9.5× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. DeepSeek V3.2 has an ECI of 146.3, Fugu Max has not been scored yet and Qwen3.8 Max Preview has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek V3.2, Fugu Max and Qwen3.8 Max 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 Qwen3.8 Max Preview have the largest context windows (1,000,000 and 1,000,000 tokens), against 128,000 for DeepSeek V3.2. Maximum output per response: DeepSeek V3.2 up to 64,000, Fugu Max up to 128,000, Qwen3.8 Max Preview up to 131,072 tokens.

Which can read images, PDFs, audio or video?

DeepSeek V3.2 accepts text; Fugu Max accepts text, images and PDFs; Qwen3.8 Max Preview accepts text, images and video. Fugu Max handles the widest range of inputs.

Are any of these open source?

DeepSeek V3.2 publishes its weights (MIT License) and can be self-hosted; Fugu Max and Qwen3.8 Max Preview is proprietary.

Which is newer?

Fugu Max is the newest, released Sep 11, 2026. Qwen3.8 Max Preview came out Jul 19, 2026; DeepSeek V3.2 came out Dec 1, 2025. Knowledge cutoff: DeepSeek V3.2 Jul 2024.

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.