GR

Grok 2

Chat model

Grok 2

Release date: 2024-08-13Updated: 2025-08-24 17:37:031,070
Parameters
269B
Context length
128K
Chinese support
Supported
Reasoning ability

Grok 2 is an AI model published by xAI, released on 2024-08-13, for Chat model, with 269B parameters, and 128K context length, under the Grok 2 Community License Agreement license, with a 88.40 score on HumanEval.

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

Grok 2

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
32K tokens
Model type
Chat model
Modality (in / out)
Text → Text
Release date
2024-08-13
Model file size
No data
MoE architecture
Yes
Total params / Active params
269B / 115B
Knowledge cutoff
No data
Grok 2

Open source & experience

Weights license
GitHub repo
GitHub link unavailable
Grok 2

Official resources

DataLearnerAI blog
No blog post yet
Grok 2

API details

API speed
3/5
No public API pricing yet.
Grok 2

Benchmark Results

Grok 2 currently shows benchmark results led by MMLU (22 / 65, score 87.50), MATH (15 / 42, score 76.10), HumanEval (14 / 39, score 88.40). 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

3 evaluations
Benchmark / mode
Score
Rank/total
87.50
22 / 65
75.50
81 / 126
56
147 / 179

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
88.40
14 / 39

Math and Reasoning

2 evaluations
Benchmark / mode
Score
Rank/total
76.10
15 / 42
0.70
55 / 60

常识推理

1 evaluations
Benchmark / mode
Score
Rank/total
Simple Bench
Standard Mode
22.70
56 / 63

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Grok 2

Publisher

Grok 2

Model Overview

Grok 2 is an AI model published by xAI, released on 2024-08-13, for Chat model, with 269B parameters, and 128K context length, under the Grok 2 Community License Agreement license, with a 88.40 score on HumanEval.

DataLearner on WeChat

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

DataLearner WeChat QR code