Publications & Commentary
Papers & Reports Newsletter Podcast
Data & Resources
Datasets
Overview AI Benchmarking AI Models Frontier Data Centers ML Hardware AI Companies GPU Clusters
Resources
AI Trends & Statistics Data Insights
Projects
FrontierMath GATE Playground Distributed Training Model Counts
About
About Us Our Team Careers Consultations Our Funding Donate
Latest
Contact
Dashboard Benchmarks Models ECI Data About

Claude Opus 4 (16k thinking)

Anthropic’s largest model in the Claude 4 series (superseded by Claude Opus 4.1), benchmarked with up to 16,000 reasoning tokens.

Release date
2025-05-22
Developer
Anthropic
Accessibility
Non-open weights
140
Epoch Capabilities Index
RANK:
ECI is a composite metric based on over 42 benchmarks. Learn more.
Thank you for your feedback!

Your comment will be reviewed. We may not be able to respond to every submission.