Grok 4.6

Name: Grok 4.6
Author: xAI

Multimodal

xAI

Grok 4.6 is xAI's latest flagship released in August 2026, leading agentic knowledge-work and coding benchmarks including AA-Briefcase, GDPval-AA, and CursorBench v3.2. It offers a 500K token context window and multimodal input support.

Key Specifications

Parameters

Context

500.0K

Release Date

August 12, 2026

Average Score

49.6%

API Documentation Results Blog

Timeline

Key dates in the model's history

Announcement

August 12, 2026

Last Update

August 27, 2026

Today

September 10, 2026

Technical Specifications

Parameters

Training Tokens

Knowledge Cutoff

February 28, 2026

Family

Capabilities

MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)

$2.00

Output (per 1M tokens)

$6.00

Max Input Tokens

500.0K

Max Output Tokens

Supported Features

Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Other Tests

Specialized benchmarks

GDPval-AA

GDPval-AA v2 Elo; Grok 4.6 High (max_score 3000). • Self-reported

58.4%

AA-Briefcase

Elo score; Artificial Analysis; Grok 4.6 High (max_score 3000). • Self-reported

52.6%

CursorBench v3.2

CursorBench v3.2; Grok 4.6 High. • Self-reported

70.0%

DeepSWE 1.1

DeepSWE v1.1; Grok 4.6 High. • Self-reported

66.0%

AA-Index

Artificial Analysis Intelligence Index; Grok 4.6 High. • Self-reported

61.0%

APEX-Agents

APEX-Agents; Grok 4.6 High. • Self-reported

57.5%

APEX-SWE

APEX-SWE; Grok 4.6 High. • Self-reported

56.4%

FrontierCode

FrontierCode v1.1 (Extended); Grok 4.6 High. • Self-reported

61.3%

Harvey LAB (Vals)

Harvey LAB (Vals); Grok 4.6 High. • Self-reported

15.8%

Terminal-Bench 3.0

Terminal-Bench v3.0; Grok 4.6 High. • Self-reported

26.0%

Terminal-Bench 4.0

Terminal-Bench 4.0 public leaderboard; resolution rate 20.3% ± 3.1%; Grok Build agent; high effort. • Verified

20.3%

License & Metadata

License

proprietary

Announcement Date

August 12, 2026

Last Updated

August 27, 2026

Compare Grok 4.6

All comparisons

vs Grok 4.5 vs Grok-3 Mini vs DeepSeek-V4-Flash-Vision-Exp vs Ling 3.0 Flash Fin vs GPT-5.6 Luna vs GLM-5.3 vs Gemini 3.5 Flash-Lite vs Claude Opus 5

Similar Models

All Models

Grok-4 Fast Reasoning

xAI

Released:Aug 2025

Price:$0.20/1M tokens

Grok-2 mini

xAI

Best score:0.9 (MMLU)

Released:Aug 2024

Grok-1.5V

xAI

Released:Apr 2024

Grok 4.5

xAI

Best score:0.9 (GPQA)

Released:Jul 2026

Price:$2.00/1M tokens

Grok 4.20

xAI

Released:Mar 2026

Grok-4.1 Fast Non-Reasoning

xAI

Released:Nov 2025

Price:$0.20/1M tokens

Grok-4.1 Fast Reasoning

xAI

Released:Nov 2025

Price:$0.20/1M tokens

Grok-4 Fast Non-Reasoning

xAI

Released:Aug 2025

Price:$0.20/1M tokens

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.