Compare AI models

Specifications
Context window
400k—
API pricing
Cheapest input
$1.25Azure—
Cheapest output
$10.00Azure—
$750Azure—
Benchmarks
Terminal-Bench 2.0
58.1%47.9%
Overview
CompanyOpenAISpaceXSI
Release dateNov 19 2025Feb 9 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GPT-5.1-Codex-Max leads Composer 1.5 on 1 of the 1 benchmark they both report (Terminal-Bench 2.0). GPT-5.1-Codex-Max shipped 82 days before Composer 1.5, 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 Terminal-Bench 2.0, GPT-5.1-Codex-Max leads at 58.1% vs Composer 1.5 at 47.9%.