> Grok 4.20 is a closed AI model from xAI, released 17 Feb 2026. Index score 158 (GPT-4 = 100), rank 42 of 229 ranked models. API price $1.25 in / $2.5 out per million tokens, 2M context.

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

# Grok 4.20

xAI

Released 17 Feb 2026

Closed

Flagship

[Compare](https://themodelindex.org/compare/grok-4-20-vs-kimi-k2-5/) [Announcement](https://docs.x.ai/developers/models/grok-4.20)

158147–170

Index score

#42 of 229 models

4/ 8

Core tests taken

4 of 6 areas · plus 11 anchor tests

−11

Versus the frontier at release

best then: GPT-5.3-Codex

Replaced by [Grok 4.5](https://themodelindex.org/models/grok-4-5/)

$1.25/ $2.5

Price per million tokens

input / output, list price

2M

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_

Gemini 3 Pro reached this score 3 months earlier.

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

Show 9 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

89%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

45%

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

57%

Agents

evidence

APEX-Agents

no result

Novel problems

evidence

ARC-AGI-2

65%

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

#42

of 219 · 158

Epoch Capabilities Index

overall capability from many benchmarks

#41

of 239 · 152.0

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

Replaced by Grok 4.5; it no longer leads any category among current models.

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

Grok

app · subscription

↗

xAI API

API

↗

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

x

xAI

$2.5 / $5.0

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

17 Feb 2026

Announcement

[docs.x.ai ↗](https://docs.x.ai/developers/models/grok-4.20)

Release entry

Grok 4.20 (beta; GA/API 03-10)

Scored as

Grok 4.20

Artificial Analysis index

–

Output speed

–

Hugging Face

closed weights

## xAI releases · around this one

Grok 4.1

Closed

17 NOV 2025

Grok 4.1 Fast

Closed

19 NOV 2025

Grok 4.20

Closed

17 FEB 2026

index 158

Grok 4.3

Closed

17 APR 2026

index 151

Grok Build 0.1

Closed

20 MAY 2026

---
Source: https://themodelindex.org/models/grok-4-20/ · The Model Index · data as of 2026-10-01