Claude
Claude

Claude Sonnet 4.6

Model ID:claude-sonnet-4-6
2026-02-17Proprietary Model
Claude FreeClaude ProClaude Max (5x)Claude Max (20x)|API
OverallNo.11
PopularityNo.18

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Knowledge Cutoff
2025-09-01

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
1MIN128KOUT

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
$3IN$15OUT

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
1462
±6
As of 2026-04-02
Overall Rank
No.18
11,092 Votes
Arena by Ability
Hard Prompts
1499±8No.9
Expert Knowledge
1503±21No.9
Instruction Following
1479±11No.6
Conversation Memory
1478±13No.16
Creative
1443±15No.19
Coding
1522±12No.8
Math
1469±21No.11
Arena by Occupation
Creative Writing
1454±12No.14
Social Sciences
1492±14No.5
Media
1440±14No.17
Business
1485±13No.6
Healthcare
1468±21No.34
Legal
1475±21No.15
Software
1510±10No.11
Mathematics
1487±25No.7
Reasoning Ability
AA Intelligence Index
43%↑4%
GPQA Diamond
80%↓2%
HLE
11%↓6%
Coding Ability
AA Coding Index
43%↑7%
SciCode
44%↑2%
TerminalBench
42%↑8%
Instruction Following
IFBench
42%↓15%
환각률 (HHEM)
11%↑0%
사실 일관성 (HHEM)
89%↑0%
Long Context
AA-LCR
59%↓5%
Agentic AI Ability
TAU2
79%↑8%
Speed
Standard Mode
45tok/sec↓33
First Output 0.82s
Artificial Analysis
Reasoning Mode
50tok/sec↓23
First Output 32.71s
Artificial Analysis