ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Command A Plus vs MiniCPM5-1B vs Perceptron Mk1

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

Price in rating: Excluded · Include price

  1. Cohere

    Command A Plus

    Released May 20, 2026

    55/100
    • ECI—
    • Price$2.50 / $10.00
    • Context128K
  2. OpenBMB

    MiniCPM5-1B

    Released May 19, 2026

    34/100
    • ECI—
    • Price—
    • Context131K
  3. Perceptron

    Perceptron Mk1

    Released May 12, 2026

    31/100
    • 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 (Command A Plus 55/100, MiniCPM5-1B 34/100, Perceptron Mk1 31/100) 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 pricePerceptron Mk1Perceptron Mk1 $0.487 · Command A Plus $4.38 per 1M tokens (3:1 blend) · MiniCPM5-1B unpriced
  • Longest contextMiniCPM5-1BMiniCPM5-1B 131,072 · Command A Plus 128,000 · Perceptron Mk1 32,768 tokens
  • Widest inputsPerceptron Mk1Command A Plus: Text, Images · MiniCPM5-1B: Text · Perceptron Mk1: Text, Images, Video
  • Self-hostingCommand A Plus and MiniCPM5-1BPublishes downloadable weights (apache-2.0)
How the score is built
MeasureWeightCommand A PlusMiniCPM5-1BPerceptron Mk1
Inputs & features60%703545
Context window40%323211
Specs only100%55/10034/10031/100

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.

Command A Plus vs MiniCPM5-1B vs Perceptron Mk1 specifications side by side
SpecificationCommand A PlusCohereMiniCPM5-1BOpenBMBPerceptron Mk1Perceptron
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$2.50—$0.15 (best)
Output$10.00—$1.50 (best)
Cached input———
Blended (3:1)$4.38—$0.487 (best)
Long-context rateSame rate—Same rate
Price sourceOfficial Cohere API—Median of 3 providers
Limits
Context window128,000 tokens131,072 tokens (best)32,768 tokens
Max output64,000 tokens131,072 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesYes
Tool callingYesYesNo
Structured outputYesNoNo
Availability
WeightsOpenOpenapache-2.0Proprietary
API model IDcommand-a-plus-05-2026——
API providers3—3
ReleasedMay 20, 2026May 19, 2026May 12, 2026
Knowledge cutoffApr 1, 2025——
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.

  • Command A Plus$45.00
  • MiniCPM5-1B—
  • Perceptron Mk1$4.50
04 — Questions

Which should you choose?

Which is better: Command A Plus, MiniCPM5-1B or Perceptron Mk1?

There is not enough shared capability evidence to name an overall winner. The scores (Command A Plus 55/100, MiniCPM5-1B 34/100, Perceptron Mk1 31/100) 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, Command A Plus, MiniCPM5-1B or Perceptron Mk1?

Perceptron Mk1 is cheaper at $0.15 input / $1.50 output per million tokens (median across 3 API providers). Command A Plus costs $2.50 input / $10.00 output per million tokens (official Cohere 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 $4.38 for Command A Plus (9× as much). MiniCPM5-1B has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Command A Plus has not been scored yet, MiniCPM5-1B 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 Command A Plus, MiniCPM5-1B 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?

MiniCPM5-1B has the largest context window at 131,072 tokens, against 128,000 for Command A Plus and 32,768 for Perceptron Mk1. Maximum output per response: Command A Plus up to 64,000, MiniCPM5-1B up to 131,072, Perceptron Mk1 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Command A Plus accepts text and images; MiniCPM5-1B accepts text; Perceptron Mk1 accepts text, images and video. Perceptron Mk1 handles the widest range of inputs.

Are any of these open source?

Command A Plus and MiniCPM5-1B publishes its weights (apache-2.0) and can be self-hosted; Perceptron Mk1 is proprietary.

Which is newer?

Command A Plus is the newest, released May 20, 2026. MiniCPM5-1B came out May 19, 2026; Perceptron Mk1 came out May 12, 2026. Knowledge cutoff: Command A Plus Apr 1, 2025.

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.