GPT-5.3-CodexvsGPT-6 Luna

GPT-5.3-Codex
GPT-6 Luna
Specifications
Context window
1.05M
API pricing
Input price
$1.75$0.10
Output price
$14.00$0.50
Cached input price
$0.175$0.01
Cheapest input
$1.75Azure
Cheapest output
$14.00Azure
Benchmarks
Next.js Evals
68%77%
Benchmarks
BullshitBench v2
24%
SWE-Bench Verified
85%
DeepSWE 1.1
66.6%
OSWorld-Verified
64.7%
Overview
CompanyOpenAIOpenAI
Release dateFeb 5 2026Sep 22 2026
AccessProprietaryProprietary

Other comparisons

GPT-5.3-CodexvsClaude Opus 5.5GPT-6 LunavsClaude Opus 5.5GPT-5.3-CodexvsGemini 3.8 FlashGPT-6 LunavsGemini 3.8 FlashGPT-5.3-CodexvsMuse Spark 1.3GPT-6 LunavsMuse Spark 1.3GPT-5.3-CodexvsGrok 4.7GPT-6 LunavsGrok 4.7GPT-5.3-CodexvsDeepSeek-V4.1-FlashGPT-6 LunavsDeepSeek-V4.1-FlashGPT-5.3-CodexvsMistral Medium 3.5GPT-6 LunavsMistral Medium 3.5

Frequently asked questions

GPT-6 Luna leads GPT-5.3-Codex on 1 of the 1 benchmark they both report (Next.js Evals). GPT-6 Luna is cheaper on both input and output: $0.10 vs $1.75 per million input tokens, and $0.50 vs $14.00 per million output tokens. Figures are base-tier rates. GPT-5.3-Codex shipped 229 days before GPT-6 Luna, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On Next.js Evals, GPT-6 Luna leads at 77% vs GPT-5.3-Codex at 68%.