ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Command A vs Pixtral Large (25.02) vs Qwen2.5-Coder-32B-Instruct

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. Cohere

    Command A

    Released Mar 13, 2025

    28/100
    • ECI—
    • Price$2.50 / $10.00
    • Context256K
  2. Mistral AI

    Pixtral Large (25.02)

    Released Apr 8, 2025

    34/100
    • ECI—
    • Price$2.00 / $6.00
    • Context128K
  3. Alibaba (Qwen)

    Qwen2.5-Coder-32B-Instruct

    Released Nov 12, 2024

    41/100
    • ECI—
    • Price$0.66 / $1.00
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-Coder-32B-Instruct 41/100, Pixtral Large (25.02) 34/100, Command A 28/100) 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 priceQwen2.5-Coder-32B-InstructQwen2.5-Coder-32B-Instruct $0.745 · Pixtral Large (25.02) $3.00 · Command A $4.38 per 1M tokens (3:1 blend)
  • Longest contextCommand ACommand A 256,000 · Qwen2.5-Coder-32B-Instruct 131,072 · Pixtral Large (25.02) 128,000 tokens
  • Widest inputsPixtral Large (25.02)Command A: Text · Pixtral Large (25.02): Text, Images · Qwen2.5-Coder-32B-Instruct: Text
  • Self-hostingCommand A and Qwen2.5-Coder-32B-InstructPublishes downloadable weights
How the score is built
MeasureWeightCommand APixtral Large (25.02)Qwen2.5-Coder-32B-Instruct
Price50%192654
Inputs & features30%355025
Context window20%433232
Specs & price only100%28/10034/10041/100

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 vs Pixtral Large (25.02) vs Qwen2.5-Coder-32B-Instruct specifications side by side
SpecificationCommand ACoherePixtral Large (25.02)Mistral AIQwen2.5-Coder-32B-InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$2.50$2.00$0.66 (best)
Output$10.00$6.00$1.00 (best)
Cached input———
Blended (3:1)$4.38$3.00$0.745 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIMedian of 3 providersMedian of 7 providers
Limits
Context window256,000 tokens (best)128,000 tokens131,072 tokens
Max output8,000 tokens8,192 tokens (best)8,192 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsOpenProprietaryOpen
API model IDcommand-a-03-2025——
API providers7 (best)37 (best)
ReleasedMar 13, 2025Apr 8, 2025Nov 12, 2024
Knowledge cutoffJun 1, 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.

  • Command A$45.00
  • Pixtral Large (25.02)$32.00
  • Qwen2.5-Coder-32B-Instruct$8.60
04 — Questions

Which should you choose?

Which is better: Command A, Pixtral Large (25.02) or Qwen2.5-Coder-32B-Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-Coder-32B-Instruct 41/100, Pixtral Large (25.02) 34/100, Command A 28/100) 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, Command A, Pixtral Large (25.02) or Qwen2.5-Coder-32B-Instruct?

Qwen2.5-Coder-32B-Instruct is cheaper at $0.66 input / $1.00 output per million tokens (median across 7 API providers). Pixtral Large (25.02) costs $2.00 input / $6.00 output per million tokens (median across 3 API providers); Command A 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 $0.745 per million tokens for Qwen2.5-Coder-32B-Instruct versus $3.00 for Pixtral Large (25.02) (4× as much) and $4.38 for Command A (5.9× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Command A has not been scored yet, Pixtral Large (25.02) has not been scored yet and Qwen2.5-Coder-32B-Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Command A, Pixtral Large (25.02) and Qwen2.5-Coder-32B-Instruct 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?

Command A has the largest context window at 256,000 tokens, against 131,072 for Qwen2.5-Coder-32B-Instruct and 128,000 for Pixtral Large (25.02). Maximum output per response: Command A up to 8,000, Pixtral Large (25.02) up to 8,192, Qwen2.5-Coder-32B-Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Command A accepts text; Pixtral Large (25.02) accepts text and images; Qwen2.5-Coder-32B-Instruct accepts text. Pixtral Large (25.02) handles the widest range of inputs.

Are any of these open source?

Command A and Qwen2.5-Coder-32B-Instruct publishes its weights and can be self-hosted; Pixtral Large (25.02) is proprietary.

Which is newer?

Pixtral Large (25.02) is the newest, released Apr 8, 2025. Command A came out Mar 13, 2025; Qwen2.5-Coder-32B-Instruct came out Nov 12, 2024. Knowledge cutoff: Command A Jun 1, 2024.

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.