ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-5.3 Codex vs Qwen MT Plus vs Command A Plus

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. OpenAI

    GPT-5.3 Codex

    Released Feb 5, 2026

    42/100
    • ECI—
    • Price$1.75 / $14.00
    • Context400K
  2. Alibaba (Qwen)

    Qwen MT Plus

    Released Jul 24, 2025

    11/100
    • ECI—
    • Price$2.46 / $7.37
    • Context16K
  3. Cohere

    Command A Plus

    Released May 20, 2026

    37/100
    • ECI—
    • Price$2.50 / $10.00
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (GPT-5.3 Codex 42/100, Command A Plus 37/100, Qwen MT Plus 11/100) 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 priceQwen MT PlusQwen MT Plus $3.69 · Command A Plus $4.38 · GPT-5.3 Codex $4.81 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.3 CodexGPT-5.3 Codex 400,000 · Command A Plus 128,000 · Qwen MT Plus 16,384 tokens
  • Widest inputsGPT-5.3 CodexGPT-5.3 Codex: Text, Images, PDFs · Qwen MT Plus: Text · Command A Plus: Text, Images
  • Self-hostingCommand A PlusPublishes downloadable weights
How the score is built
MeasureWeightGPT-5.3 CodexQwen MT PlusCommand A Plus
Price50%172219
Inputs & features30%80070
Context window20%50032
Specs & price only100%42/10011/10037/100

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.

GPT-5.3 Codex vs Qwen MT Plus vs Command A Plus specifications side by side
SpecificationGPT-5.3 CodexOpenAIQwen MT PlusAlibaba (Qwen)Command A PlusCohere
Capability
Capabilities Index (ECI)———
ECI rank———
SWE-bench VerifiedFixing real GitHub issues74.8%——
Price per million tokens
Input$1.75 (best)$2.46$2.50
Output$14.00$7.37 (best)$10.00
Cached input$0.175——
Blended (3:1)$4.81$3.69 (best)$4.38
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIOfficial Alibaba APIOfficial Cohere API
Limits
Context window400,000 tokens (best)16,384 tokens128,000 tokens
Max output128,000 tokens (best)8,192 tokens64,000 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYeslow · medium · high · xhighNoYes
Tool callingYesNoYes
Structured outputYesNoYes
Availability
WeightsProprietaryProprietaryOpen
API model IDgpt-5.3-codexqwen-mt-pluscommand-a-plus-05-2026
API providers31 (best)33
ReleasedFeb 5, 2026Jul 24, 2025May 20, 2026
Knowledge cutoffAug 31, 2025—Apr 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.

  • GPT-5.3 Codex$45.50
  • Qwen MT Plus$39.34
  • Command A Plus$45.00
04 — Questions

Which should you choose?

Which is better: GPT-5.3 Codex, Qwen MT Plus or Command A Plus?

There is not enough shared capability evidence to name an overall winner. The scores (GPT-5.3 Codex 42/100, Command A Plus 37/100, Qwen MT Plus 11/100) 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, GPT-5.3 Codex, Qwen MT Plus or Command A Plus?

Qwen MT Plus is cheaper at $2.46 input / $7.37 output per million tokens (official Alibaba API price). Command A Plus costs $2.50 input / $10.00 output per million tokens (official Cohere API price); GPT-5.3 Codex costs $1.75 input / $14.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $3.69 per million tokens for Qwen MT Plus versus $4.38 for Command A Plus (1.2× as much) and $4.81 for GPT-5.3 Codex (1.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GPT-5.3 Codex has not been scored yet, Qwen MT Plus has not been scored yet and Command A Plus has not been scored yet.

Which is better for coding?

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

Which has the bigger context window?

GPT-5.3 Codex has the largest context window at 400,000 tokens, against 128,000 for Command A Plus and 16,384 for Qwen MT Plus. Maximum output per response: GPT-5.3 Codex up to 128,000, Qwen MT Plus up to 8,192, Command A Plus up to 64,000 tokens.

Which can read images, PDFs, audio or video?

GPT-5.3 Codex accepts text, images and PDFs; Qwen MT Plus accepts text; Command A Plus accepts text and images. GPT-5.3 Codex handles the widest range of inputs.

Are any of these open source?

Command A Plus publishes its weights and can be self-hosted; GPT-5.3 Codex and Qwen MT Plus is proprietary.

Which is newer?

Command A Plus is the newest, released May 20, 2026. GPT-5.3 Codex came out Feb 5, 2026; Qwen MT Plus came out Jul 24, 2025. Knowledge cutoff: GPT-5.3 Codex Aug 31, 2025, Command A Plus Apr 1, 2025.

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.