Grok 4.3

Parameters

Undisclosed

Context Length

1M

Modality

Multimodal

Architecture

Undisclosed

License

Proprietary

Release Date

30 Apr 2026

Knowledge Cutoff

Dec 2025

API Pricing (per 1M)

Input: $1.25 · Output: $2.50

Evaluation Benchmarks

Rank

#102

BenchmarkScoreRank

0.84

52

Agentic Coding

LiveBench Agentic

0.19

57

0.70

58

0.62

59

LiveBench Average

LiveBench Average

0.62

59

0.56

60

0.71

61

Agent Arena

Agent Arena
high

-11.57

Standard

-20.26

71

78

General Text

Text Arena

1442

81

Agentic Index

Artificial Analysis
high

0.15

Standard

0.14

87

89

high

0.42

Standard

0.35

104

114

Web Development

WebDev Arena

1357

104

Intelligence Index

Artificial Analysis
high

0.25

medium

0.25

low

0.24

Standard

0.14

132

134

139

227

Rankings

Overall Rank

#102

Coding Rank

#123

About Grok 4.3

Released April 30, 2026 by xAI, Grok 4.3 is a powerful reasoning architecture featuring a 1M token context window and massive gains on instruction-following (81.3%) and scientific computing benchmarks. Optimized for complex multi-step programmatic investigations.

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