> GPT-6 Luna is a closed AI model from OpenAI, released 22 Sep 2026. Index score 166 (GPT-4 = 100), rank 27 of 229 ranked models. API price $0.10 in / $0.50 out per million tokens, 1.05M context.

[Models](https://themodelindex.org/models/) /[OpenAI](https://themodelindex.org/labs/openai/)

# GPT-6 Luna

OpenAI

Released 22 Sep 2026

Closed

Flagship

[Compare](https://themodelindex.org/compare/gpt-6-luna-vs-kimi-k3/) [Announcement](https://openai.com/index/introducing-gpt-6-sol-and-luna/)

166155–178

Index score

#27 of 229 models

4/ 8

Core tests taken

4 of 6 areas · plus 2 anchor tests

−33

Versus the frontier at release

best then: Claude Opus 5.5

$0.10/ $0.50

Price per million tokens

input / output, list price

1.05M

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

Claude Opus 4.6 reached this score 8 months earlier.

## Test results · by area · tick = best by any model

Show 2 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

90%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

79%

Coding

no evidence yet

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

44%

Novel problems

evidence

ARC-AGI-2

59%

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#27

of 219 · 166

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#21

of 207 · 38

LMArena · Coding

coding questions in chat

#52

of 383 · 1511

LMArena · Maths

maths questions in chat

#71

of 373 · 1448

LMArena · Text

overall chat quality, judged by people

#78

of 388 · 1444

LMArena · Creative writing

creative writing

#82

of 386 · 1409

LMArena · WebDev

building web apps and front ends

#28

of 123 · 1582

LiveBench · Overall

overall, with fresh questions to limit contamination

#44

of 58 · 72

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

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

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### From the lab

ChatGPT

app · subscription

↗

OpenAI API

API

↗

#### API providers · 3 · per million tokens, in / out

O

OpenAI

$0.20 / $1.0

cheapest

A

Azure

$0.11 / $0.55

↗

A

Amazon Bedrock

$0.11 / $0.55

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

22 Sep 2026

Announcement

[openai.com ↗](https://openai.com/index/introducing-gpt-6-sol-and-luna/)

Release entry

GPT-6 Sol + GPT-6 Luna

Scored as

GPT-6 Luna

Artificial Analysis index

38 · max

Output speed

125 tokens/s

Hugging Face

closed weights

## OpenAI releases · around this one

GPT-5.6 Terra

Closed

9 JUL 2026

index 178

GPT-6 Astra

Closed

4 SEP 2026

index 197

GPT-6 Luna

Closed

22 SEP 2026

index 166

GPT-6 Sol

Closed

22 SEP 2026

index 180

GPT-6.1 Sol

Closed

29 SEP 2026

index 184

---
Source: https://themodelindex.org/models/gpt-6-luna/ · The Model Index · data as of 2026-10-01