aiintelligence

GPT-5.3-Codex

It writes software code and assists with software engineering tasks.

openai’s large language model, able to hold about 400k tokens of context (roughly 300k words) in one conversation, working across text and image and file->text. You reach it through an API or through tools built on it. Built for software engineers and developers. openai describes it as: “It achieves state-of-the-art results...” source ↗

Our tested score
97/100 · Humanising AI text
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
95/100 · Book writing
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
94/100 · Health questions
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
93/100 · Legal questions
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
95/100 · Emotional support
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
88/100 · Travel planning
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
93/100 · Translation
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
94/100 · Creative writing
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
95/100 · Research
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
93/100 · CV writing
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
97/100 · Presentations
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
98/100 · Vibe coding
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
95/100 · Job applications
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
99/100 · Social posts
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
97/100 · Flashcards
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
92/100 · Coding
18 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
88/100 · Study notes
12 tasks, marked blind by 3 judges · 14 Aug 2026 · receipts
98/100 · Customer replies
12 tasks, marked blind by 3 judges · 14 Aug 2026 · receipts
98/100 · Maths
12 tasks, marked blind by 3 judges · 14 Aug 2026 · receipts
99/100 · Emails
12 tasks, marked blind by 3 judges · 14 Aug 2026 · receipts
100/100 · Extraction
12 tasks, marked blind by 3 judges · 13 Aug 2026 · receipts
96/100 · Summarising
12 tasks, marked blind by 3 judges · 13 Aug 2026 · receipts
88/100 · Essays
12 tasks, marked blind by 3 judges · 13 Aug 2026 · receipts
98/100 · Spreadsheets
12 tasks, marked blind by 3 judges · 13 Aug 2026 · receipts
API price (per 1M in/out)
$1.75 / $14
OpenRouter API17 Aug 2026
Battle record
unfought
no battle yet — we don't guess
Forum sentiment (90d)
33%
developer-forum posts: 6 opinions in 105
What people are posting (90 days)
Loudest post this quarter
“Kimi K3 just fixed 15 critical security bugs that Codex and Fable refused because of “cyber guardrails”. Hugging Face: We had this experience ourselves this week! Very scary to be guardrailed as a defender when you know attackers are likely bypassing”

Compare GPT-5.3-Codex against…

GPT-5.6 Luna · spreadsheets & ExcelGPT-5.6 Terra · spreadsheets & ExcelGPT-5.6 Sol · spreadsheets & ExcelGPT-5.5 · spreadsheets & ExcelGLM 5.2 · spreadsheets & ExcelQwen3.7 Max · spreadsheets & ExcelGrok 4.5 · spreadsheets & ExcelClaude Opus 4.8 · spreadsheets & ExcelDeepSeek V4 Flash · spreadsheets & ExcelGPT-5.6 Sol · essay writingGPT-5.5 · essay writingGPT-5.6 Luna · essay writingGPT-5.6 Terra · essay writingClaude Sonnet 5 · essay writingClaude Opus 4.6 · essay writingGrok 4.5 · essay writingQwen3.7 Max · essay writingGemini 3.1 Pro Preview · essay writingClaude Opus 4.8 · summarising documents
Every claim we hold (3)