A zoom tool pushes chart-reading accuracy to 73%
Anthropic shared numbers from the Chartography benchmark, a set of 100 questions on dense charts built from real data. Give the model a zoom tool and Fable 5 jumped from 29% to 73% accuracy, while Sonnet 5 went from 13% to 44%.
Shrinking large images loses fine detail. The tool lets Claude request a specific region and get that slice back from the original at full resolution. The updated recipe is in Claude Cookbooks on GitHub.
Up next
Claude’s voice mode moves to Opus and Sonnet, Video
Claude’s voice mode now runs on Opus and Sonnet and can reach connected email and calendar mid-conversation. New languages include Spanish, French, Hindi, and Japanese, with open beta live today on mobile, desktop, and web.
Related stories
- Anthropic points developers to fresh examples in Claude Cookbooks
- METR clocks Anthropic benchmark gains at 1.9x old pace
- A heart icon takes Claude from 0% to 100% recursive code
- Intelligence Index v5: Opus 5.5 at 58, GPT-6 Astra at 57
- Claude’s web app hides a Voice tab marked Preview
- Haiku 5.5 ranks #2 of 182 and burns 440M tokens doing it
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.