Grok 4 Code

Name: Grok 4 Code
Author: xAI

Coding modelGrok 4

Grok 4 Code

Release date: 2025-07-03Updated: 2025-07-02Views: 1,167

Live demoGitHubHugging FaceCompare

Parameters

No data

Context length

128K

Multilingual

Supported

Reasoning ability

4/5

Grok 4 Code is an AI model published by xAI, released on 2025-07-03, for Coding model, and 128K context length, with a 72.00 score on SWE-bench.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Grok 4 Code

Model basics

Reasoning traces

Supported

Thinking modes

Standard Mode (Default)Thinking Level · Deep

Context length

128K tokens

Max output length

64K tokens

Model type

Coding model

Modality (in / out)

Text → Text

Release date

2025-07-03

Model file size

No data

MoE architecture

Total params / Active params

No data / Not applicable

Knowledge cutoff

No data

Grok 4 Code

Open source & experience

Code license

Proprietary

Weights license

Proprietary

GitHub repo

N/A

Hugging Face

N/A

Live demo

N/A

Grok 4 Code

Official resources

Paper

N/A

DataLearnerAI blog

N/A

Grok 4 Code

API details

API speed

3/5

No public API pricing yet.

Grok 4 Code

Benchmark Results

Grok 4 Code currently shows benchmark results led by SWE-bench Verified (55 / 114, score 72), SWE-bench (2 / 2, score 72). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.