The Model Index
Models/OpenAI

GPT-6 Luna

OpenAIClosed weightsFlagship

GPT-6 Luna is a closed AI model from OpenAI with an index score of 162 (GPT-4 = 100), rank 41 of 217.

162146–178Index score#41 of 217 models
$0.10/ $0.50Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
22 Sep 2026Released2 months ago

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100GPT-6 Luna

Claude Opus 4.6 reached this score 8 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
90%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath (tiers 1-3)
79%
Codingevidence
SWE-bench Verified
no result
Terminal-Bench 4.0
14%
Agentsevidence
APEX-Agents
44%
Professional workevidence
Finance Agent (v2)
50%
Novel problemsevidence
ARC-AGI-2
59%
Long tasksno evidence yet
METR time horizon
no result

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on 12 leaderboards

Best attop three among current models

Not in the top three among current models on any category we track.

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released22 Sep 2026
Announcementopenai.com ↗
Release entryGPT-6 Sol + GPT-6 Luna
Scored asGPT-6 Luna
Output speed–
Hugging Faceclosed weights

OpenAI releasesaround this one

This page as a chartDownload PNG