Grok 4.6

Active Parameters

Undisclosed

Context Length

500K

Modality

Multimodal

Architecture

Mixture of Experts

License

Proprietary

Release Date

1 Aug 2026

Knowledge Cutoff

Feb 2026

API Pricing (per 1M)

Input: $2.00 · Output: $6.00

Evaluation Benchmarks

Rank

#20

BenchmarkScoreRank

Agentic Index

Artificial Analysis
high

0.53

medium

0.51

low

0.41

8

15

36

max

0.76

high

0.77

medium

0.74

low

0.66

19

9

24

56

0.91

12

0.78

17

LiveBench Average

LiveBench Average

0.78

17

Agentic Coding

LiveBench Agentic

0.57

20

0.93

25

Web Development

WebDev Arena
high

1618

32

0.74

37

0.77

43

Agent Arena

Agent Arena
max

-0.92

49

General Text

Text Arena
high

1457

61

Intelligence Index

Artificial Analysis
max

0.31

90

Rankings

Overall Rank

#20

Coding Rank

#18

About Grok 4.6

Grok 4.6 is xAI's flagship frontier multimodal intelligence model trained on the massive Colossus supercluster. Featuring native vision understanding, real-time X and web grounding, and extended reasoning capabilities, Grok 4.6 is designed for complex mathematical reasoning, enterprise coding, and high-autonomy agent workflows with a 500,000-token context window.

Specifications

Architecture specifications are undisclosed for proprietary models.

About Grok 4

xAI's frontier intelligence models trained with reinforcement learning at unprecedented scale using the 200,000 GPU Colossus cluster. Grok 4 series demonstrates state-of-the-art performance in reasoning, coding, and multimodal understanding with native tool use capabilities. Features real-time search integration across X and the web, advanced reasoning through scaled RL training, and industry-leading performance on academic benchmarks. Designed for both immediate responses and extended thinking modes with vision capabilities.


Other Grok 4 Models