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 (TTC)

Model basics

Reasoning traces

Supported

Context length

132K tokens

Max output length

65536 tokens

Model type

编程大模型

Release date

2025-07-05

Model file size

No data

MoE architecture

Total params / Active params

0.0B / N/A

Knowledge cutoff

No data

Inference modes

常规模式（Non-Thinking Mode）思考模式（Thinking Mode）深度思考（Deeper Thinking Mode）

Grok 4 Code (TTC)

Open source & experience

Code license

不开源

Weights license

不开源- 不开源

GitHub repo

GitHub link unavailable

Hugging Face

Hugging Face link unavailable

Live demo

https://grok.com/

Grok 4 Code (TTC)

Official resources

Paper

No paper available

DataLearnerAI blog

No blog post yet

Grok 4 Code (TTC)

API details

API speed

3/5

No public API pricing yet.

Grok 4 Code (TTC)

Benchmark Results

No benchmark data to show.

Grok 4 Code (TTC)

Publisher

xAI

View publisher details

Grok 4 Code (Test-Time-Compute)

Model Overview

Grok-4 Code (Test-Time-Compute)是Grok-4 Code的推理加强版本，利用更多的推理思维链来提升模型的效果。Grok 4 Code是xAI针对编程领域特调的大模型，加入TTC之后模型效果有明显提升，在SWE Bench Verified上得分由72分提升到75分，是目前得分最高的一个模型。

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送