Compare AI models

Specifications
Context window
1M400k
Benchmarks
BullshitBench v2
20%39%
Overview
CompanyGoogleOpenAI
Release dateMay 19 2026Sep 15 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GPT-5-Codex leads Gemini 3.5 Flash on 1 of the 1 benchmark they both report (BullshitBench v2). GPT-5-Codex shipped 246 days before Gemini 3.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.5 Flash) vs 400k (GPT-5-Codex).

On BullshitBench v2, GPT-5-Codex leads at 39% vs Gemini 3.5 Flash at 20%.