Grok
Grok 4.20
Model ID:grok-4.20-0309-non-reasoning
2026-03-09Proprietary Model
Grok SuperGrok Heavy|API
PopularityNo.4
Knowledge Cutoff
Unknown
The date this AI finished learning. It may not know about things that happened after this date.
Input → Output Format
The types of content this AI can receive, and what it can produce in return.
Context Memory
2M
The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.
Cost/1M Words
$2IN$6OUT
The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).
AI Performance Evaluation
Arena Overall Score
1491
±7As of 2026-04-02
Overall Rank
No.4
7,383 Votes
Arena by Ability
Hard Prompts
1506±10No.5
Expert Knowledge
1483±27No.24
Instruction Following
1467±14No.10
Conversation Memory
1508±21🥉 No.3
Creative
1485±19No.4
Coding
1526±15No.6
Math
1456±25No.21
Arena by Occupation
Creative Writing
1472±15No.6
Social Sciences
1488±18No.8
Media
1471±17🥉 No.3
Business
1489±17No.4
Healthcare
1528±28🥈 No.2
Legal
1518±27🥇 No.1
Software
1519±12No.4
Mathematics
1472±32No.14
Source:Arena Intelligence
Speed
Standard Mode
219tok/sec↑141
First Output 0.32s
Artificial Analysis
Reasoning Mode
248tok/sec↑175
First Output 11.74s
Artificial Analysis
Source:Artificial Analysis