Grok 4.6
Parameters
Undisclosed
Context Length
500K
Modality
Multimodal
Architecture
Undisclosed
License
Proprietary
Release Date
12 Aug 2026
Knowledge Cutoff
-
API Pricing (per 1M)
Input: $2.00 · Output: $6.00
Evaluation Benchmarks
Rank
#13
| Benchmark | Score | Rank |
|---|---|---|
Agentic Index | max 0.53 high 0.53 medium 0.51 low 0.41 | 10 8 15 36 |
Reasoning | 0.91 | 8 |
General | 0.78 | 14 |
LiveBench Average | 0.78 | 14 |
Agentic Coding | 0.57 | 18 |
Web Development | high 1618 | 20 |
Mathematics | 0.93 | 20 |
Intelligence Index | max 0.44 high 0.44 medium 0.43 low 0.35 | 25 24 29 59 |
Agent Arena | max 0.01 | 28 |
Data Analysis | 0.74 | 32 |
Coding | 0.77 | 35 |
General Text | high 1456 | 51 |
Rankings
Overall Rank
#13
Coding Rank
#24
About Grok 4.6
Grok 4.6 is a frontier multimodal reasoning model developed by xAI. It provides advanced performance across software engineering, STEM problem solving, and complex knowledge-work tasks.
Technical 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.