AI Model Release Tracker

GPT-5.3-Codex

Released

GPT-5.3-Codex is an AI model released by OpenAI on Thursday, Feb 5 2026, 56 days after GPT-5.2. Benchmark results (shown below) cover BullshitBench v2, SWE-Bench Verified, Next.js Evals, OSWorld-Verified, and threejseval.

API pricing

InputWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
$1.75
Cached inputA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again.
$0.175
OutputWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one.
$14.00
  • Reasoning or thinking is supported.
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Verified August 18, 2026Read from developers.openai.com. Click the check to open the source.

Available from

Azure—$1.75$14.00400K
OpenAI—$1.75$14.00400K
OpenAIfast$3.50$28.00400K
USD per 1M tokensEvery price here is for one million tokens. A token is roughly three-quarters of a word, so a million tokens is about 750,000 words of text.Checked October 16, 2026Third-party rates from openrouter.ai, not the lab’s own list price.

Benchmarks

Coding

SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better.via BenchLM
85%
#7 of 59
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better.
68%
#18 of 33

Agentic & tool use

OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better.via BenchLM
64.7%
#23 of 29

Robustness

BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better.
24%
#67 of 97

Community preference

threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better.
1171
#24 of 27

Source: BenchLM, retrieved 31 August 2026. Other sources are identified on the linked benchmark pages.

Compare GPT-5.3-Codex with

GPT-5.3-Codex

Suggested comparisons

GPT-5.3-CodexvsGPT-6.1 SolGPT-5.3-CodexvsClaude Haiku 5.5GPT-5.3-CodexvsGemini 4 ArgonGPT-5.3-CodexvsMuse Spark OpenGPT-5.3-CodexvsGrok 4.7GPT-5.3-CodexvsDeepSeek-V4.1-FlashGPT-5.3-CodexvsMistral Large 4GPT-5.3-CodexvsKimi K3GPT-5.3-CodexvsGLM-5.3-FlashGPT-5.3-CodexvsQwen3.8-Max-0902GPT-5.3-CodexvsNemotron 3.5 Super VL

Frequently asked questions

GPT-5.3-Codex was released by OpenAI on Thursday, Feb 5 2026.

All OpenAI releases

47 tracked

2022

1 release
GPT-3.5
Nov 30 2022