Claude Sonnet 4.5

Language Proprietary

Benchmarks

About Claude Sonnet 4.5

Claude Sonnet 4.5 is an AI model developed by Anthropic, in the language category, released in 2025, made available as a proprietary (API-only) model.

On this page you'll find Claude Sonnet 4.5's full specifications, including 21 benchmark results. Review provider pricing and benchmark scores below, or compare Claude Sonnet 4.5 head-to-head with other language models.

→ More models by Anthropic → All language models → AI benchmarks leaderboard

Links

Announcement ↗

Community

Would you run Claude Sonnet 4.5 again?

No votes yet — be the first.

Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Claude Sonnet 4.5 benchmark scores▶

Compare on the benchmark table →

Benchmark	Category	Score	Variant
BrowseComp	agentic	24.1%	cited-deepseek-v3-2
BrowseComp-Zh	agentic	42.4	cited-deepseek-v3-2
MCP-Mark	agentic	33.3	cited-deepseek-v3-2
MCP-Universe	agentic	46.5	cited-deepseek-v3-2
Terminal-Bench 2.0	agentic	42.8%	cited-devstral-readme
Terminal-Bench 2.0	agentic	42.8%	cited-deepseek-v3-2
Tool-Decathlon	agentic	38.6	cited-deepseek-v3-2
τ²-Bench (TAU2)	agentic	84.7	cited-deepseek-v3-2
Codeforces Elo	code	1,480	rating-cited-deepseek-v3-2
LiveCodeBench	code	64%	cited-deepseek-v3-2
SWE-bench Verified	code	77.2%	cited-devstral-readme
SWE-bench Verified	code	77.2%	cited-deepseek-v3-2
SWE-Bench Multilingual	coding	68	cited-deepseek-v3-2
SWE-Bench Multilingual	coding	68	cited-devstral-readme
MMLU-Pro	general	88.2%	cited-deepseek-v3-2
AIME 2025	math	87%	cited-deepseek-v3-2
HMMT February 2025	math	79.2%	cited-deepseek-v3-2
HMMT November 2025	math	81.7	cited-deepseek-v3-2
GPQA Diamond	reasoning	83.4%	cited-deepseek-v3-2
Humanity's Last Exam	reasoning	32%	search-agent-cited-deepseek-v3-2
Humanity's Last Exam	reasoning	13.7%	text-only-cited-deepseek-v3-2

More models like Claude Sonnet 4.5

Llama-3-70B-Synthia-v3.5

· 70B

Frequently asked questions

What is Claude Sonnet 4.5? ▶

Claude Sonnet 4.5 is an AI model developed by Anthropic, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Claude Sonnet 4.5? ▶

Claude Sonnet 4.5 was developed by Anthropic and released in 2025.

Is Claude Sonnet 4.5 open source or proprietary? ▶

Claude Sonnet 4.5 is a proprietary model. It is accessed through an API rather than by downloading the weights.

How much does Claude Sonnet 4.5 cost? ▶

Pricing for Claude Sonnet 4.5 depends on the provider. See the providers table on this page for the latest API rates.

How does Claude Sonnet 4.5 perform on benchmarks? ▶

Claude Sonnet 4.5 is benchmarked across 21 evaluations on GenAIList, including BrowseComp (24.1%). See the full benchmark table below and compare it with other models.