Claude Sonnet 4.6 is Anthropic's latest Sonnet-class model released in February 2026, delivering frontier performance across coding, agents, and professional work at the Sonnet price point. It features a 1M-token context window with extended thinking and 64K max output tokens, and introduces the effort parameter for fine-tuning the balance between speed, cost, and reasoning depth. The model excels at iterative development, complex codebase navigation, polished document creation, and confident computer use for web QA and workflow automation.
Anthropic FreeAnthropic ProAnthropic Max (5x)Anthropic Max (20x)API|VisionReasoningWeb Search|Proprietary Model
Knowledge Cutoff
2025-08-01
Input → Output Format
Context Memory
1MIN64KOUT
AI Performance Evaluation
Arena Overall Score
1463
±5As of 2026-05-01
Overall Rank
No.23
15,794 Votes
Arena by Ability
Hard Prompts
1499±7No.11
Expert Knowledge
1505±17No.9
Instruction Following
1475±9No.10
Conversation Memory
1482±11No.20
Creative
1442±12No.25
Coding
1521±10No.11
Math
1468±18No.20
Arena by Occupation
Creative Writing
1452±10No.22
Social Sciences
1493±12No.11
Media
1441±11No.21
Business
1479±11No.13
Healthcare
1473±17No.39
Legal
1474±18No.28
Software
1510±8No.15
Mathematics
1495±21No.13
Source:Arena Intelligence
Overall
AA Intelligence Index
43%↑3%
LiveBench
70%↑9%
ForecastBench
60%↑0%
Reasoning & Math
GPQA Diamond
80%↓2%
HLE
11%↓7%
LB Reasoning
77%↑8%
LB Math
80%↑6%
LB Data
75%↑21%
Coding
AA Coding Index
43%↑7%
LB Coding
74%↑1%
LB Agentic
63%↑18%
TAU2
79%↓1%
TerminalBench
42%↑8%
SciCode
44%↑2%
Language & Instructions
IFBench
42%↓21%
AA-LCR
59%↓3%
Hallucination (HHEM)
11%↑0%
Factual (HHEM)
89%↑0%
LB Language
71%↓1%
LB IF
52%↑1%
Output Speed
Standard Mode
52tok/s↓25
First Output 0.94s
Reasoning Mode
50tok/s↓37
First Output 32.71s
