THE ORIGINAL SOURCE

Claude Sonnet 5.5

Simon Willison's Weblog ·

Simon Willison comments on Claude Sonnet 5.5, citing Anthropic’s reported speed and cost improvements. He also describes a pelican-SVG test that exhausted its token budget.

At a glance

Key passages3

Attributed passages with the context to verify them. Open the original text to check the source.

AI model capability comparison

Sonnet 5.5 near-parity with Opus 5.5 on coding tasks

Original excerpt

Sonnet 5.5 appears to be almost as good as Opus 5.5 on some coding tasks, including various viral 3D animation tricks .

Additional context is not included in this excerpt. Read the original conversation.

AI model performance and cost

Reported Sonnet 5.5 speed and cost improvements

Original excerpt

Claude Sonnet 5.5 . New Sonnet model from Anthropic today. They say it "runs 30%+ faster, and costs up to 30% less for most work" - it's priced the same as Sonnet 5 but appears to beat it on every benchmark, and should be cheaper to run as well.

Additional context is not included in this excerpt. Read the original conversation.

AI model reliability and token limits

Token exhaustion in a pelican-SVG test

Original excerpt

the "max" thinking effort pelican thought for 128,000 tokens (at a cost of $1.28) before running out of tokens and failing to produce an SVG.
Context

Here are some pelicans riding bicycles . Sonnet 5.5 suffered from the same bug as Opus 5.5 :

Source & methodology

These viewpoints are linked to their original sources. Paraphrases are labeled and are not verbatim quotes.

Open transcript or source material (opens in a new tab)Report an issue