Compare AI models

Specifications
Context window
1M—
Benchmarks
Terminal-Bench 2.0
54.2%40%
Overview
CompanyGoogleSpaceXSI
Release dateNov 18 2025Oct 29 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Gemini 3.0 Pro leads Composer on 1 of the 1 benchmark they both report (Terminal-Bench 2.0). Composer shipped 20 days before Gemini 3.0 Pro, 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, Gemini 3.0 Pro leads at 54.2% vs Composer at 40%.