ZMIME
Comparison · 3 models · Updated Nov 18, 2026

CoBuddy vs Sakana Namazu vs Perceptron Mk1

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. Baidu

    CoBuddy

    Released May 6, 2026

    48/100
    • ECI—
    • Price$0.28 / $1.13
    • Context131K
  2. Sakana AI

    Sakana Namazu

    Released Aug 3, 2026

    51/100
    • ECI—
    • Price$0.95 / $4.00
    • Context262K
  3. Perceptron

    Perceptron Mk1

    Released May 12, 2026

    47/100
    • ECI—
    • Price$0.15 / $1.50
    • Context33K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Sakana Namazu 51/100, CoBuddy 48/100, Perceptron Mk1 47/100) 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 pricePerceptron Mk1Perceptron Mk1 $0.487 · CoBuddy $0.492 · Sakana Namazu $1.71 per 1M tokens (3:1 blend)
  • Longest contextSakana NamazuSakana Namazu 262,144 · CoBuddy 131,072 · Perceptron Mk1 32,768 tokens
  • Widest inputsSakana Namazu and Perceptron Mk1CoBuddy: Text · Sakana Namazu: Text, Images, PDFs · Perceptron Mk1: Text, Images, Video
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightCoBuddySakana NamazuPerceptron Mk1
Price50%623762
Inputs & features30%358045
Context window20%324311
Specs & price only100%48/10051/10047/100

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.

CoBuddy vs Sakana Namazu vs Perceptron Mk1 specifications side by side
SpecificationCoBuddyBaiduSakana NamazuSakana AIPerceptron Mk1Perceptron
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.28$0.95$0.15 (best)
Output$1.13 (best)$4.00$1.50
Cached input—$0.15—
Blended (3:1)$0.492$1.71$0.487 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Sakana AI APIMedian of 3 providers
Limits
Context window131,072 tokens262,144 tokens (best)32,768 tokens
Max output65,536 tokens (best)65,536 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesYes
Tool callingYesYesNo
Structured outputNoYesNo
Availability
WeightsProprietaryProprietaryProprietary
API model ID—sakana-namazu—
API providers17 (best)3
ReleasedMay 6, 2026Aug 3, 2026May 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.

  • CoBuddy$5.06
  • Sakana Namazu$17.50
  • Perceptron Mk1$4.50
04 — Questions

Which should you choose?

Which is better: CoBuddy, Sakana Namazu or Perceptron Mk1?

There is not enough shared capability evidence to name an overall winner. The scores (Sakana Namazu 51/100, CoBuddy 48/100, Perceptron Mk1 47/100) 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, CoBuddy, Sakana Namazu or Perceptron Mk1?

Perceptron Mk1 is cheaper at $0.15 input / $1.50 output per million tokens (median across 3 API providers). CoBuddy costs $0.28 input / $1.13 output per million tokens (median across 1 API provider); Sakana Namazu costs $0.95 input / $4.00 output per million tokens (official Sakana AI API price). At a typical mix of three input tokens to one output token, that is $0.487 per million tokens for Perceptron Mk1 versus $0.492 for CoBuddy (1× as much) and $1.71 for Sakana Namazu (3.5× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. CoBuddy has not been scored yet, Sakana Namazu has not been scored yet and Perceptron Mk1 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for CoBuddy, Sakana Namazu and Perceptron Mk1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Perceptron Mk1 does not support tool calling, which most coding agents need.

Which has the bigger context window?

Sakana Namazu has the largest context window at 262,144 tokens, against 131,072 for CoBuddy and 32,768 for Perceptron Mk1. Maximum output per response: CoBuddy up to 65,536, Sakana Namazu up to 65,536, Perceptron Mk1 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

CoBuddy accepts text; Sakana Namazu accepts text, images and PDFs; Perceptron Mk1 accepts text, images and video. Sakana Namazu handles the widest range of inputs.

Are any of these open source?

No. CoBuddy, Sakana Namazu and Perceptron Mk1 are proprietary and only available through APIs and apps.

Which is newer?

Sakana Namazu is the newest, released Aug 3, 2026. Perceptron Mk1 came out May 12, 2026; CoBuddy came out May 6, 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.