Model comparison
GPT-5.3-Codex vs GPT-5.2-Codex
- Input
- $1.75 / 1M tokens
- Output
- $14.00 / 1M tokens
- Context
- 400K
- Released
- 2026-02-05
- Input
- $1.75
- Output
- $14.00
- Context
- 400K
- Released
- 2025-12-11
GPT-5.3-Codex scores higher on 2 of the 2 benchmarks both models report; both charge the same $1.8 per 1M input tokens.
Specs and pricing side by side
| Spec | GPT-5.3-Codex | GPT-5.2-Codex |
|---|---|---|
| Maker | OpenAI | OpenAIsame |
| Released | 2026-02-05 | 2025-12-11 |
| Context window | 400K | 400Ksame |
| Max output | 128K | 128Ksame |
| Input price | $1.75 / 1M tokens | $1.75 |
| Output price | $14.00 / 1M tokens | $14.00 |
| Parameters | not published | Undisclosed |
| License | Proprietary | Proprietarysame |
| Weights | API only | API onlysame |
| Modalities | Text, Vision | Text, Visionsame |
| Knowledge cutoff | 2025-08-31 | Aug 2025 |
Benchmarks both models report
| Benchmark | GPT-5.3-Codex | GPT-5.2-Codex |
|---|---|---|
| SWE-Bench Pro | 56.8% | 56.4% |
| Terminal-Bench 2.0 | 77.3% | 64% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick GPT-5.3-Codex if…
- You care about SWE-Bench Pro, Terminal-Bench 2.0 (it scores higher on 2 shared benchmarks).
- Your use case is: autonomous, long-running software-engineering tasks inside the Codex app, CLI, IDE extension, and web.
Pick GPT-5.2-Codex if…
- Your use case is: reach for it for long, independent execution of complex engineering tasks inside Codex (the CLI, IDE, or cloud).
FAQ
Which is better, GPT-5.3-Codex or GPT-5.2-Codex?
GPT-5.3-Codex scores higher on 2 of the 2 benchmarks both models report; both charge the same $1.8 per 1M input tokens. The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How do GPT-5.3-Codex and GPT-5.2-Codex pricing compare?
GPT-5.3-Codex: $1.75 / 1M tokens input, $14.00 / 1M tokens output. GPT-5.2-Codex: $1.75 input, $14.00 output (list API prices as published by each maker).
What are the context windows of GPT-5.3-Codex and GPT-5.2-Codex?
GPT-5.3-Codex offers 400K with up to 128K output; GPT-5.2-Codex offers 400K with up to 128K output.
Is GPT-5.3-Codex newer than GPT-5.2-Codex?
GPT-5.3-Codex was released 2026-02-05; GPT-5.2-Codex was released 2025-12-11.