1 / 3
Swipe to compare

Claude Sonnet 4.5 is Anthropic's most advanced Sonnet model prior to the 4.6 generation, optimized for real-world agents and coding workflows. It delivers state-of-the-art coding performance with improvements in system design, code security, and specification adherence. The model is designed for extended autonomous operation with fact-based progress tracking, and introduces stronger agentic capabilities including speculative parallel execution, improved tool orchestration, and efficient context and memory management for multi-context, long-running workflows.

Author
AnthropicAnthropic
Release Date
2025-09-29
Knowledge Cutoff
2025-01-31
License
Proprietary
I/O Format
Context Length
1M / 64K
API I/O (1M)
$3 / $15
How to Use
Anthropic Free or above / API Access
Output Speed
44 tok/s
Arena Overall
1453
Intelligence Index
43.0
Coding Index
38.6
Math Index
88.0
LiveBench
51.3
ForecastBench
60.1
GPQA Diamond
83.4%
HLE
17.3%
MMLU-Pro
87.5%
AIME 2025
88.0%
MATH-500
LB Reasoning
42.3
LB Math
62.6
LB Data Analysis
47.0
LiveCodeBench
71.4%
LB Coding
76.1
LB Agentic
48.3
TAU2
78.1%
TerminalBench
35.6%
SciCode
44.7%
IFBench
57.3%
AA-LCR
0.7
Hallucination (HHEM)
12.0%
Factual Consistency (HHEM)
88.0%
LB Language
76.0
LB Instruction Following
23.5