Compare AI models

Specifications
Context window
1M—
Benchmarks
SWE-Bench Multilingual
87.3%65.9%
Terminal-Bench 2.0
82%47.9%
Overview
CompanyAnthropicSpaceXSI
Release dateApr 7 2026Feb 9 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude Mythos Preview leads Composer 1.5 on 2 of the 2 benchmarks they both report (SWE-Bench Multilingual, Terminal-Bench 2.0). Composer 1.5 shipped 57 days before Claude Mythos Preview, 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 SWE-Bench Multilingual, Claude Mythos Preview leads at 87.3% vs Composer 1.5 at 65.9%. On Terminal-Bench 2.0, Claude Mythos Preview leads at 82% vs Composer 1.5 at 47.9%.