DataLearner logo
GR

Grok 4.6

Coding modelGrok 4

Grok 4.6

Release date: 2026-08-12Updated: 2026-08-13 10:32:10.921Knowledge cutoff: 2026-02-0114
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
500K
Chinese support
Not supported
Reasoning ability

Grok 4.6 is an AI model published by xAI, released on 2026-08-12, for Coding model, and 500K context length, with a 1753.00 score on GDPval-AA v2.

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

Grok 4.6

Model basics

Reasoning traces
Supported
Thinking modes
Thinking Level · High (Default)Thinking Level · LowThinking Level · MediumThinking Level · Extra-High
Context length
500K tokens
Max output length
No data
Model type
Coding model
Modality (in / out)
Text, Image → Text
Release date
2026-08-12
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
2026-02-01
Grok 4.6

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Grok 4.6

Official resources

Paper
DataLearnerAI blog
No blog post yet
Grok 4.6

API details

API speed
4/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
TextContext < 200000$2.00/ 1M$6.00/ 1M
TextContext >= 200000, Context <= 500000$4.00/ 1M$12.00/ 1M
Cache PricingPrompt Cache
TypeTTLWriteRead
Text--$0.500/ 1M
Context < 200000
Text--$1.00/ 1M
Context >= 200000, Context <= 500000
Grok 4.6

Benchmark Results

Grok 4.6 currently shows benchmark results led by AA Intelligence Index (1 / 4, score 61), GDPval-AA v2 (2 / 7, score 1753), DeepSWE (8 / 21, score 65.90). 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

Coding and Software Engineer

4 evaluations
Benchmark / mode
Score
Rank/total
69.90
1 / 1
DeepSWE
HighTools
65.90
8 / 21
61.30
1 / 1
APEX-SWE
HighTools
56.40
1 / 1

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
61
1 / 4

Productivity Knowledge

3 evaluations
Benchmark / mode
Score
Rank/total
GDPval-AA v2
HighTools
1753
2 / 7
AA-Briefcase
HighTools
1577
2 / 3
Harvey Lab-AA
HighTools
15.80
2 / 2

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
APEX-Agents
HighTools
57.50
1 / 2

AI Agent - Tool Usage

1 evaluations
Benchmark / mode
Score
Rank/total
26
1 / 1

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Grok 4.6

Publisher

Grok 4.6

Model Overview

Grok 4.6 is an AI model published by xAI, released on 2026-08-12, for Coding model, and 500K context length, with a 1753.00 score on GDPval-AA v2.

DataLearner on WeChat

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

DataLearner WeChat QR code