# Claude Haiku 5.5 · max reasoning effort

Simon Willison tested Anthropic's newly released Claude Haiku 5.5 in his blog post 'Claude Haiku 5.5' using the llm CLI. The model defaults to medium reasoning effort and cannot disable thinking. The author tested effort levels from low to max and featured the max-effort output in the article, which took 5 minutes 9 seconds and cost ~3.38 cents. The output depicts a white pelican with a red cap, curved beak, long orange legs on pedals, dark grey bike frame, sun and speed streaks. Archives the article's original WebP preview from static.simonwillison.net; model label is source-reported and unauthenticated; date is the source publication on 2026-10-07.

- Recorded date: 2026-10-07
- Date precision: Day
- Date basis: source-publication
- Model (source label): Claude Haiku 5.5
- Model attribution: Source-reported, not independently authenticated
- Creator / publisher: Simon Willison
- Format: Static SVG
- Prompt category: Source-documented test
- Original prompt: The source does not provide the complete per-run prompt; see the original link
- Last updated: 2026-10-05
- caseRole: case
- caseNumber: 1020
- timelineVisible: True
- datePrecision: day
- dateBasis: source-publication
- Original source: https://simonwillison.net/2026/Oct/7/claude-haiku-5-5/
- Archive record: https://pelicanmap.aveniqa.com/en/specimens/simon-claude-haiku-5-5-2026-10-07/
- Rights: Works belong to their original creators. Archiving does not change their licenses.
- Media: https://pelicanmap.aveniqa.com/media/collected/2026-10-09-october-frontier-batch/simon-claude-haiku-5-5-max-2026-10-07.webp
  Source: https://static.simonwillison.net/static/2026-10-07/haiku-5.5-max.webp