> GPT-6 Sol is a closed AI model from OpenAI, released 22 Sep 2026. Index score 180 (GPT-4 = 100), rank 9 of 229 ranked models. API price $2.0 in / $10 out per million tokens, 1.05M context.

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

# GPT-6 Sol

OpenAI

Released 22 Sep 2026

Closed

Flagship

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

180166–193

Index score

#9 of 229 models

4/ 8

Core tests taken

4 of 6 areas · plus 2 anchor tests

−20

Versus the frontier at release

best then: Claude Opus 5.5

Replaced by [GPT-6.1 Sol](https://themodelindex.org/models/gpt-6-1-sol/)

$2.0/ $10

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 Fable 5 reached this score 3 months earlier.

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

Show 2 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

94%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

90%

Coding

no evidence yet

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

54%

Novel problems

evidence

ARC-AGI-2

90%

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

#9

of 219 · 180

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#8

of 207 · 48

LMArena · WebDev

building web apps and front ends

#7

of 123 · 1689

LMArena · Coding

coding questions in chat

#27

of 383 · 1523

LMArena · Creative writing

creative writing

#52

of 386 · 1438

LMArena · Text

overall chat quality, judged by people

#60

of 388 · 1456

LMArena · Maths

maths questions in chat

#64

of 373 · 1454

LiveBench · Overall

overall, with fresh questions to limit contamination

#11

of 58 · 79.3

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

3rd

data analysis questions

LiveBench · Data Analysis

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

$4.0 / $20

cheapest

A

Azure

$2.2 / $11

↗

A

Amazon Bedrock

$2.2 / $11

↗

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 Sol

Artificial Analysis index

48 · max

Output speed

74 tokens/s

Hugging Face

closed weights

## OpenAI releases · around this one

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-sol/ · The Model Index · data as of 2026-10-01