Compare AI models

Specifications
Context window
1M1.05M
API pricing
Input price
$2.00$2.00
Output price
$10.00$10.00
Cached input price
$0.10$0.10
Cheapest input
$1.00Google—
Cheapest output
$5.00Google—
$450Google$900OpenAI list price
Benchmarks
FrontierCode 2.0
41.1%43.8%
Terminal-Bench-Science 0.1
64.8%68%
Agents’ Last Exam v1.1
77.4%73%
Overview
CompanyGoogleOpenAI
Release dateOct 28 2026Nov 17 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

GPT-6.2 Sol leads Gemini 4 Carbon on 2 of the 3 benchmarks they both report (FrontierCode 2.0, Terminal-Bench-Science 0.1, Agents’ Last Exam v1.1). Both charge $2.00 per million input tokens. Both charge $10.00 per million output tokens. Figures are base-tier rates. Gemini 4 Carbon shipped 20 days before GPT-6.2 Sol, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 4 Carbon) vs 1.05M (GPT-6.2 Sol).

On FrontierCode 2.0, GPT-6.2 Sol leads at 43.8% vs Gemini 4 Carbon at 41.1%. On Terminal-Bench-Science 0.1, GPT-6.2 Sol leads at 68% vs Gemini 4 Carbon at 64.8%. On Agents’ Last Exam v1.1, Gemini 4 Carbon leads at 77.4% vs GPT-6.2 Sol at 73%.