ZMIME
Comparison · 2 models · Updated Oct 4, 2026

GPT-5.2 Chat vs GPT-5.3 Codex

GPT-5.3 Codex comes out ahead, 42 to 35 on our weighted score.

  1. OpenAI

    GPT-5.2 Chat

    Released Dec 11, 2025Deprecated

    35/100
    • ECI—
    • Price$1.75 / $14.00
    • Context128K
    Full specs Remove GPT-5.2 Chat
  2. Our pick

    OpenAI

    GPT-5.3 Codex

    Released Feb 5, 2026

    42/100
    • ECI156.8
    • Price$1.75 / $14.00
    • Context400K
    Full specs Remove GPT-5.3 Codex

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

GPT-5.3 Codex is our pick

GPT-5.3 Codex is the better all-round choice, scoring 42/100 against GPT-5.2 Chat (35). It leads on inputs & features and context window. 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 priceSame priceGPT-5.2 Chat $4.81 · GPT-5.3 Codex $4.81 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.3 CodexGPT-5.3 Codex 400,000 · GPT-5.2 Chat 128,000 tokens
  • Widest inputsGPT-5.3 CodexGPT-5.2 Chat: Text, Images · GPT-5.3 Codex: Text, Images, PDFs
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightGPT-5.2 ChatGPT-5.3 Codex
Price50%1818
Inputs & features30%7080
Context window20%2444
Overall100%35/10042/100

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 Chat vs GPT-5.3 Codex specifications side by side
SpecificationGPT-5.2 ChatOpenAIGPT-5.3 CodexOpenAI
Capability
Capabilities Index (ECI)—156.8
ECI rank—#18 of 148
SWE-bench VerifiedFixing real GitHub issues—74.8%
Price per million tokens
Input$1.75$1.75
Output$14.00$14.00
Cached input$0.175$0.175
Blended (3:1)$4.81$4.81
Long-context rateSame rateSame rate
Price sourceOfficial OpenAI APIOfficial OpenAI API
Limits
Context window128,000 tokens400,000 tokens (best)
Max output16,384 tokens128,000 tokens (best)
Inputs and features
TextYesYes
ImagesYesYes
PDFsNoYes
AudioNoNo
VideoNoNo
ReasoningYesmediumYeslow · medium · high · xhigh
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model IDgpt-5.2-chat-latestgpt-5.3-codex
API providers319 (best)
ReleasedDec 11, 2025Feb 5, 2026
Knowledge cutoffAug 31, 2025Aug 31, 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-5.2 Chat$45.50
  • GPT-5.3 Codex$45.50
04 — Questions

Which should you choose?

Which is better: GPT-5.2 Chat or GPT-5.3 Codex?

GPT-5.3 Codex is the better all-round choice, scoring 42/100 against GPT-5.2 Chat (35). It leads on inputs & features and context window. 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 Chat or GPT-5.3 Codex?

GPT-5.2 Chat and GPT-5.3 Codex cost the same: $1.75 input / $14.00 output per million tokens.

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. GPT-5.2 Chat has not been scored yet and GPT-5.3 Codex has an ECI of 156.8.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5.2 Chat yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.

Which has the bigger context window?

GPT-5.3 Codex has the largest context window at 400,000 tokens, against 128,000 for GPT-5.2 Chat. Maximum output per response: GPT-5.2 Chat up to 16,384, GPT-5.3 Codex up to 128,000 tokens.

Which can read images, PDFs, audio or video?

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

Are any of these open source?

No. GPT-5.2 Chat and GPT-5.3 Codex are proprietary and only available through APIs and apps.

Which is newer?

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

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons