Grok 3.5

Name: Grok 3.5
Author: xAI

Reasoning model

Grok 3.5

Release date: 2025-05-06Updated: 2025-05-05Views: 1,187

Live demoGitHubHugging FaceCompare

Parameters

No data

Context length

128K

Multilingual

Supported

Reasoning ability

4/5

Grok 3.5 is an AI model published by xAI, released on 2025-05-06, for Reasoning model, and 128K context length, with a 0.00 score on GPQA Diamond.

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

Grok 3.5

Model basics

Reasoning traces

Supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

64K tokens

Model type

Reasoning model

Modality (in / out)

Text, Image → Text, Image

Release date

2025-05-06

Model file size

No data

MoE architecture

Total params / Active params

No data / Not applicable

Knowledge cutoff

No data

Grok 3.5

Open source & experience

Code license

Proprietary

Weights license

Proprietary

GitHub repo

N/A

Hugging Face

N/A

Live demo

grok.com

Grok 3.5

Official resources

Paper

N/A

DataLearnerAI blog

N/A

Grok 3.5

API details

API speed

3/5

No public API pricing yet.

Grok 3.5

Benchmark Results

Grok 3.5 currently shows benchmark results led by GPQA Diamond (268 / 270, score 0), SimpleQA (47 / 47, score 0), AIME 2024 (62 / 62, score 0). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.