The Model Index
Models/OpenAI

GPT-5.6 Luna

OpenAIClosed weightsFlagship

GPT-5.6 Luna is a closed AI model from OpenAI with an index score of 162 (GPT-4 = 100), rank 42 of 217.

162146–178Index score#42 of 217 models
$0.20/ $1.2Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
9 Jul 2026ReleasedReplaced by GPT-6 Luna

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100GPT-5.6 Luna

Claude Opus 4.6 reached this score 5 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
92%
Humanity's Last Exam
no result
Mathsevidence
FrontierMath (tiers 1-3)
82%
Codingevidence
SWE-bench Verified
no result
Terminal-Bench 4.0
12%
Agentsevidence
APEX-Agents
43%
Professional workevidence
Finance Agent (v2)
55%
Novel problemsevidence
ARC-AGI-2
60%
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 11 leaderboards

Best attop three among current models

Where to use itprices checked 18 Nov 2026

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released9 Jul 2026
Announcementopenai.com ↗
Release entryGPT-5.6 (Sol/Terra/Luna; preview 06-26)
Scored asGPT-5.6 Luna
Output speed–
Hugging Faceclosed weights

OpenAI releasesaround this one

This page as a chartDownload PNG