Muse Spark 1.2vsGPT-5.3-Codex

Muse Spark 1.2
GPT-5.3-Codex
Specifications
Context window
1M
API pricing
Input price
$1.75
Output price
$14.00
Cached input price
$0.175
Cheapest input
$1.25Meta$1.75Azure
Cheapest output
$4.25Meta$14.00Azure
Benchmarks
BullshitBench v2
50%24%
Benchmarks
SWE-Bench Verified
85%
DeepSWE 1.1
59.3%
Next.js Evals
68%
Terminal-Bench 2.1
82.9%
OSWorld-Verified
64.7%
Overview
CompanyMetaOpenAI
Release dateAug 5 2026Feb 5 2026
AccessProprietaryProprietary

Other comparisons

Muse Spark 1.2vsClaude Fable 5.1GPT-5.3-CodexvsClaude Fable 5.1Muse Spark 1.2vsGemini 3.8 FlashGPT-5.3-CodexvsGemini 3.8 FlashMuse Spark 1.2vsGrok 4.6GPT-5.3-CodexvsGrok 4.6Muse Spark 1.2vsDeepSeek-V4.1-FlashGPT-5.3-CodexvsDeepSeek-V4.1-FlashMuse Spark 1.2vsMistral Medium 3.5GPT-5.3-CodexvsMistral Medium 3.5Muse Spark 1.2vsKimi K3GPT-5.3-CodexvsKimi K3

Frequently asked questions

Muse Spark 1.2 leads GPT-5.3-Codex on 1 of the 1 benchmark they both report (BullshitBench v2). Only GPT-5.3-Codex has a verified first-party API price: $1.75 per million input tokens and $14.00 per million output tokens. No pay-as-you-go API rate is tracked for Muse Spark 1.2. GPT-5.3-Codex shipped 181 days before Muse Spark 1.2, 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 BullshitBench v2, Muse Spark 1.2 leads at 50% vs GPT-5.3-Codex at 24%.