Compare AI models

Specifications
Context window
1M400k
API pricing
Input price
—$1.25
Output price
—$10.00
Cached input price
—$0.125
Cheapest input
—$1.25Azure
Cheapest output
—$10.00Azure
—$750OpenAI list price
Benchmarks
BullshitBench v2
20%21%
Humanity's Last Exam · no tools
40.2%24.8%
CharXiv Reasoning · with tools
84.9%81.1%
Overview
CompanyGoogleOpenAI
Release dateMay 19 2026Aug 7 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Gemini 3.5 Flash leads GPT-5 on 2 of the 3 benchmarks they both report (BullshitBench v2, Humanity's Last Exam, CharXiv Reasoning). Only GPT-5 has a verified first-party price for an available API: $1.25 per million input tokens and $10.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for Gemini 3.5 Flash. GPT-5 shipped 285 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).

On BullshitBench v2, GPT-5 leads at 21% vs Gemini 3.5 Flash at 20%. On Humanity's Last Exam · no tools, Gemini 3.5 Flash leads at 40.2% vs GPT-5 at 24.8%. On CharXiv Reasoning · with tools, Gemini 3.5 Flash leads at 84.9% vs GPT-5 at 81.1%.