GR

Grok 3

Chat modelGrok-3

Grok 3

Release date: 2025-02-17Updated: 2025-02-18 17:12:381,352
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
128K
Chinese support
Supported
Reasoning ability

Grok 3 is an AI model published by xAI, released on 2025-02-17, for Chat model, and 128K context length, under the 不开源 license, with a 84.20 score on AIME 2024.

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

Grok 3

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
No data
Model type
Chat model
Modality (in / out)
No data
Release date
2025-02-17
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Grok 3

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
No live demo
Grok 3

Official resources

Paper
No paper available
DataLearnerAI blog
Grok 3

API details

API speed
No data
No public API pricing yet.
Grok 3

Benchmark Results

Grok 3 currently shows benchmark results led by AIME 2024 (22 / 62, score 84.20), SimpleQA (16 / 45, score 43.40), GPQA Diamond (75 / 179, score 80.40). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
80.40
75 / 179

Common Sense

1 evaluations
Benchmark / mode
Score
Rank/total
43.40
16 / 45

Math and Reasoning

4 evaluations
Benchmark / mode
Score
Rank/total
84.20
22 / 62
77.10
62 / 106
3.80
45 / 60
0
72 / 80

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
70.60
52 / 120

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
Standard Mode
36.10
44 / 63

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Standard Mode
53.30
30 / 59

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Grok 3

Publisher

Grok 3

Model Overview

Grok 3 is an AI model published by xAI, released on 2025-02-17, for Chat model, and 128K context length, under the 不开源 license, with a 84.20 score on AIME 2024.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code