GPT-5.3-Codex
FrontierOpenAI•Released on 2025-12-18
OpenAI's coding-optimized model, surpassing Claude on SWE-bench. HN users praise its coding value and much more generous quotas than Claude. Ideal for intensive coding work.
71
Overall Score
Voice of the community
sample 389“Codex can actually write, debug, test, and even understand entire codebases inside a sandbox. It looks wild.”
Core Specs
256K
Context Window
64K
Max Output
ReasoningOpen Sourcetext
Scenario Scores
Pros & Cons
Sentiment61% +28% ·11% −
Pros
- +Coding-optimized
- +Great value
- +Generous quotas
- +SWE-bench leader
Cons
- −Text-only
- −Weak at creative tasks
- −Requires Codex-specific API
Pricing
Input (per 1M tokens)$1.75
Output (per 1M tokens)$14.00
Subscription$20/month
Free trial available
Updated on 2026-03-06
Get Started
1Visit the provider's website
2Create an account
3Start using the model
Benchmarks
sweBench76.3%
humanEval97.2%
aiderPolyglot88%