CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks -- by Pattaraphon Kenny Wongchamcharoen, Kris Gulati, Min Min Fong, Abhishek Nagaraj

Đăng bởi
NBER
Ngày đăng
Độ dài
121 từ · 1 phút
2026, 18th Annual Feldstein Lecture, Mark Duggan, "Social Security Reform in an Era of Fiscal Deficits" Primary tabs
  • Acknowledgements and Disclosures

    We thank Shruti Vora for invaluable research assistance and members of the Data Innovation & AI Lab (DIAL) for helpful discussions and iterative feedback. This work received no external funding, although Expected Parrot and Together AI provided in-kind model-inference credits used in the research. Any opinions, conclusions, or views expressed herein are those of the authors and do not necessarily reflect the views of the National Bureau of Economic Research.


  • Citation and Citation DataCopy Citation Pattaraphon Kenny Wongchamcharoen, Kris Gulati, Min Min Fong, and Abhishek Nagaraj, "CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work Tasks," NBER Working Paper 35663 (2026), https://doi.org/10.3386/w35663. Copy to Clipboard Download Citation
  • Associated Links
SI 2026 Methods Lecture
Using AI in Household Finance Research: A Practical Guide

Bài viết này từ đâu mà có

Bài viết này được NBER đăng lần đầu vào 27 tháng 8, 2026. HUE Legacy Ventures không phải tác giả của bài viết.

Carried in full with attribution and a link to the original. Rights remain with the publisher, who may request removal at any time.

Đọc tại nber.org →