ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-5.2 Codex vs GPT-5.3 Codex vs Command A Translate

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-5.2 Codex

    Released Dec 11, 2025

    39/100
    • ECI—
    • Price$1.75 / $14.00
    • Context400K
  2. OpenAI

    GPT-5.3 Codex

    Released Feb 5, 2026

    42/100
    • ECI—
    • Price$1.75 / $14.00
    • Context400K
  3. Cohere

    Command A Translate

    Released Aug 28, 2025

    20/100
    • ECI—
    • Price$2.50 / $10.00
    • Context8K
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, GPT-5.2 Codex 39/100, Command A Translate 20/100) 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 priceCommand A TranslateCommand A Translate $4.38 · GPT-5.2 Codex $4.81 · GPT-5.3 Codex $4.81 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.2 Codex and GPT-5.3 CodexGPT-5.2 Codex 400,000 · GPT-5.3 Codex 400,000 · Command A Translate 8,000 tokens
  • Widest inputsGPT-5.2 Codex and GPT-5.3 CodexGPT-5.2 Codex: Text, Images, PDFs · GPT-5.3 Codex: Text, Images, PDFs · Command A Translate: Text
  • Self-hostingCommand A TranslatePublishes downloadable weights
How the score is built
MeasureWeightGPT-5.2 CodexGPT-5.3 CodexCommand A Translate
Price50%171719
Inputs & features30%708035
Context window20%50500
Specs & price only100%39/10042/10020/100

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-5.2 Codex vs GPT-5.3 Codex vs Command A Translate specifications side by side
SpecificationGPT-5.2 CodexOpenAIGPT-5.3 CodexOpenAICommand A TranslateCohere
Capability
Capabilities Index (ECI)———
ECI rank———
SWE-bench VerifiedFixing real GitHub issues—74.8%—
Price per million tokens
Input$1.75 (best)$1.75 (best)$2.50
Output$14.00$14.00$10.00 (best)
Cached input—$0.175—
Blended (3:1)$4.81$4.81$4.38 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 18 providersOfficial OpenAI APIOfficial Cohere API
Limits
Context window400,000 tokens (best)400,000 tokens (best)8,000 tokens
Max output128,000 tokens (best)128,000 tokens (best)8,000 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYeslow · medium · high · xhighNo
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsProprietaryProprietaryOpen
API model ID—gpt-5.3-codexcommand-a-translate-08-2025
API providers1931 (best)1
ReleasedDec 11, 2025Feb 5, 2026Aug 28, 2025
Knowledge cutoffAug 31, 2025Aug 31, 2025Jun 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.

  • GPT-5.2 Codex$45.50
  • GPT-5.3 Codex$45.50
  • Command A Translate$45.00
04 — Questions

Which should you choose?

Which is better: GPT-5.2 Codex, GPT-5.3 Codex or Command A Translate?

There is not enough shared capability evidence to name an overall winner. The scores (GPT-5.3 Codex 42/100, GPT-5.2 Codex 39/100, Command A Translate 20/100) 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-5.2 Codex, GPT-5.3 Codex or Command A Translate?

Command A Translate is cheaper at $2.50 input / $10.00 output per million tokens (official Cohere API price). GPT-5.2 Codex costs $1.75 input / $14.00 output per million tokens (median across 18 API providers); 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 $4.38 per million tokens for Command A Translate versus $4.81 for GPT-5.2 Codex (1.1× as much) and $4.81 for GPT-5.3 Codex (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GPT-5.2 Codex has not been scored yet, GPT-5.3 Codex has not been scored yet and Command A Translate has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5.2 Codex and Command A Translate 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?

GPT-5.2 Codex and GPT-5.3 Codex have the largest context windows (400,000 and 400,000 tokens), against 8,000 for Command A Translate. Maximum output per response: GPT-5.2 Codex up to 128,000, GPT-5.3 Codex up to 128,000, Command A Translate up to 8,000 tokens.

Which can read images, PDFs, audio or video?

GPT-5.2 Codex accepts text, images and PDFs; GPT-5.3 Codex accepts text, images and PDFs; Command A Translate accepts text. GPT-5.2 Codex handles the widest range of inputs.

Are any of these open source?

Command A Translate publishes its weights and can be self-hosted; GPT-5.2 Codex and GPT-5.3 Codex is proprietary.

Which is newer?

GPT-5.3 Codex is the newest, released Feb 5, 2026. GPT-5.2 Codex came out Dec 11, 2025; Command A Translate came out Aug 28, 2025. Knowledge cutoff: GPT-5.2 Codex Aug 31, 2025, GPT-5.3 Codex Aug 31, 2025, Command A Translate 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.