> Grok 4.5 is a closed AI model from xAI, released 8 Jul 2026. Index score 163 (GPT-4 = 100), rank 36 of 229 ranked models. API price $2.0 in / $6.0 out per million tokens, 500K context.

[Models](https://themodelindex.org/models/) /[xAI](https://themodelindex.org/labs/xai/)

# Grok 4.5

xAI

Released 8 Jul 2026

Closed

Flagship

[Compare](https://themodelindex.org/compare/grok-4-5-vs-kimi-k3/) [Announcement](https://x.ai/news/grok-4-5)

163152–174

Index score

#36 of 229 models

4/ 8

Core tests taken

4 of 6 areas · plus 15 anchor tests

−22

Versus the frontier at release

best then: Claude Fable 5

Replaced by [Grok 4.6](https://themodelindex.org/models/grok-4-6/)

$2.0/ $6.0

Price per million tokens

input / output, list price

500K

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 5 months earlier.

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

Show 12 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

93%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

57%

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

56%

Novel problems

evidence

ARC-AGI-2

53%

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

#36

of 220 · 163

LMArena · Creative writing

creative writing

#33

of 386 · 1451

LMArena · Instruction following

following detailed instructions

#42

of 388 · 1462

LMArena · Long prompts

long, complex requests

#40

of 366 · 1481

LMArena · Maths

maths questions in chat

#43

of 373 · 1473

LMArena · Text

overall chat quality, judged by people

#45

of 388 · 1466

LMArena · Coding

coding questions in chat

#45

of 383 · 1514

Epoch Capabilities Index

overall capability from many benchmarks

#35

of 242 · 154.0

LMArena · Vision

understanding images

#25

of 149 · 1279

LMArena · Search

answering with web search

#8

of 34 · 1213

LMArena · WebDev

building web apps and front ends

#34

of 123 · 1552

LiveBench · Overall

overall, with fresh questions to limit contamination

#30

of 58 · 75.8

LMArena · Documents

working with long documents

#24

of 41 · 1452

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

1st

answering with web search

LMArena · Search

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 2 Oct 2026

#### From the lab

Grok

app · subscription

↗

xAI API

API

↗

#### API providers · 1 · per million tokens, in / out

x

xAI

$4.0 / $12

cheapest

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

8 Jul 2026

Announcement

[x.ai ↗](https://x.ai/news/grok-4-5)

Release entry

Grok 4.5

Scored as

Grok 4.5

Artificial Analysis index

–

Output speed

–

Hugging Face

closed weights

## xAI releases · around this one

Grok 4.3

Closed

17 APR 2026

index 151

Grok Build 0.1

Closed

20 MAY 2026

Grok 4.5

Closed

8 JUL 2026

index 163

Grok 4.6

Closed

12 AUG 2026

index 170

Grok 4.7

Closed

21 SEP 2026

index 157

---
Source: https://themodelindex.org/models/grok-4-5/ · The Model Index · data as of 2026-10-02