RSS

Anthropic

Claude Sonnet 4.5

Benchmarks, price, context and versions

Also searched as

Claude Sonnet 4.5 benchmark, claude sonnet 4.5 release date, claude sonnet 4.5 pricing, claude sonnet 4.5 context window

Direct answer: Claude Sonnet 4.5 is a model from Anthropic. 82.3% on GPQA Diamond, per Epoch AI. On OpenRouter, US$ 3.00 per 1 million input tokens and US$ 15.00 per 1 million output tokens.

✓ Good for

  • very long documents or code (a window of 1 million tokens or more, according to OpenRouter)

✕ Not the best for

  • the ceiling of reasoning on research-level math (#71 of 86 on FrontierMath (tiers 1 to 3))
  • answering short facts with little invention (#66 of 87 on SimpleQA Verified)
  • fixing bugs in real code (#23 of 32 on SWE-bench Verified)
  • technical reasoning as the model appears through the API (#84 of 135 on GPQA Diamond (OpenRouter))
  • when the input budget sits at the top of the table (input price in the highest 25% on OpenRouter)

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

Benchmarks

GPQA Diamond

?what it is
82.3%

highest score on this metric 96.4%

83º / 198 · Epoch AI, latest version we checked

OTIS Mock AIME

?
77.8%

highest score on this metric 100%

92º / 186 · Epoch AI, latest version we checked

FrontierMath (tiers 1 to 3)

?
23.9%

highest score on this metric 95.1%

71º / 86 · Epoch AI, latest version we checked

SimpleQA Verified

?
30.7%

highest score on this metric 94%

66º / 87 · Epoch AI, latest version we checked

SWE-bench Verified

?
71.3%

highest score on this metric 83.5%

23º / 32 · Epoch AI, latest version we checked

GPQA Diamond (OpenRouter)

?
81.7%

highest score on this metric 96.5%

84º / 135 · OpenRouter Benchmarks, latest version we checked

τ-bench Verified (airline)

?
74.9%

highest score on this metric 82%

53º / 131 · OpenRouter Benchmarks, latest version we checked

Key specs

Origin
the US
Family
Claude Sonnet provisional data
Weights?
closed
License
no data
Input US$/1M?
US$ 3.00
Output US$/1M
US$ 15.00
Context?
1,000,000 tokens
Parameters
no data
Input
file, image, text
OpenRouter usage?
no data
Downloads (30 days)?
no data
Use cases provisional data
Text Agents Code
Dates in sources
  • 2025, published, per Epoch AI
  • 2025, listed on OpenRouter

Version history

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

FAQ

How much does Claude Sonnet 4.5 cost?

On OpenRouter, US$ 3.00 per 1 million input tokens and US$ 15.00 per 1 million output tokens.

What is the context window of Claude Sonnet 4.5?

1,000,000 tokens, per OpenRouter.

What is Claude Sonnet 4.5?

Claude Sonnet 4.5 is a model from Anthropic, with closed weights, used for text, agents, code.

Is Claude Sonnet 4.5 open source?

No. It is available through API only.

What is Claude Sonnet 4.5's GPQA Diamond score?

82.3% on GPQA Diamond, per Epoch AI.

Is Claude Sonnet 4.5 good for coding?

It scores 71.3% on SWE-bench Verified, per Epoch AI.

Who made Claude Sonnet 4.5?

It was made by Anthropic, a lab from the US.

provisional data Questions ordered by what shows up in public Google search suggestions (no volume). Answers use source data only.

Models from Anthropic

See lab

Anthropic does not publish weights on Hugging Face: data only via OpenRouter and Epoch AI.

Sources

  • Epoch AI, CC BY 4.0, latest version we checked.
  • OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
  • OpenRouter Benchmarks, CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.