> GPT-5.6 Terra is a closed AI model from OpenAI, released 9 Jul 2026. Index score 178 (GPT-4 = 100), rank 10 of 229 ranked models. API price $2.0 in / $12 out per million tokens, 1.05M context.

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

# GPT-5.6 Terra

OpenAI

Released 9 Jul 2026

Closed

Flagship

[Compare](https://themodelindex.org/compare/gpt-5-6-terra-vs-kimi-k3/) [Announcement](https://openai.com/index/improving-gpt-5-6-sol-in-chatgpt/)

178167–189

Index score

#10 of 229 models

4/ 8

Core tests taken

4 of 6 areas · plus 16 anchor tests

−7

Versus the frontier at release

best then: Claude Fable 5

$2.0/ $12

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 1 month earlier.

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

Show 14 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

93%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

86%

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

58%

Novel problems

evidence

ARC-AGI-2

84%

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

#10

of 219 · 178

Epoch Capabilities Index

overall capability from many benchmarks

#9

of 239 · 159.8

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#15

of 207 · 42

LMArena · Maths

maths questions in chat

#33

of 373 · 1479

LMArena · Coding

coding questions in chat

#41

of 383 · 1515

LMArena · Text

overall chat quality, judged by people

#47

of 388 · 1465

LMArena · Creative writing

creative writing

#68

of 386 · 1426

LMArena · Vision

understanding images

#31

of 149 · 1268

LMArena · Documents

working with long documents

#12

of 41 · 1472

LiveBench · Overall

overall, with fresh questions to limit contamination

#18

of 58 · 77.9

LMArena · WebDev

building web apps and front ends

#43

of 123 · 1519

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

2nd

working with long documents

LMArena · Documents

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 / $24

cheapest

A

Azure

$2.2 / $13.2

↗

A

Amazon Bedrock

$2.2 / $13.2

↗

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

9 Jul 2026

Announcement

[openai.com ↗](https://openai.com/index/improving-gpt-5-6-sol-in-chatgpt/)

Release entry

GPT-5.6 (Sol/Terra/Luna; preview 06-26)

Scored as

GPT-5.6 Terra

Artificial Analysis index

42 · max

Output speed

89 tokens/s

Hugging Face

closed weights

## OpenAI releases · around this one

GPT-5.6 Luna

Closed

9 JUL 2026

index 169

GPT-5.6 Sol

Closed

9 JUL 2026

index 184

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

---
Source: https://themodelindex.org/models/gpt-5-6-terra/ · The Model Index · data as of 2026-10-01