There is no free benchmark: An institutional view of legal AI benchmarking.

Guha N, Zhang AK, Tsang C, Manning CD, Nyarko J, Ho DE

Open source

DOI
10.1073/pnas.2509757122
Published
2026 Jul 28
Container
Proceedings of the National Academy of Sciences of the United States of America
Publisher
Not recorded
Open access
yes

Credibility signals

limited evidence Score 45/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1073/pnas.2509757122,
  title = {There is no free benchmark: An institutional view of legal AI benchmarking.},
  author = {Guha N and Zhang AK and Tsang C and Manning CD and Nyarko J and Ho DE},
  year = {2026},
  journal = {Proceedings of the National Academy of Sciences of the United States of America},
  doi = {10.1073/pnas.2509757122},
  url = {https://doi.org/10.1073/pnas.2509757122}
}

RIS

TY  - JOUR
TI  - There is no free benchmark: An institutional view of legal AI benchmarking.
AU  - Guha N
AU  - Zhang AK
AU  - Tsang C
AU  - Manning CD
AU  - Nyarko J
AU  - Ho DE
PY  - 2026
JO  - Proceedings of the National Academy of Sciences of the United States of America
DO  - 10.1073/pnas.2509757122
UR  - https://doi.org/10.1073/pnas.2509757122
ER  - 

APA

N, G., AK, Z., C, T., CD, M., J, N., & DE, H. (2026). There is no free benchmark: An institutional view of legal AI benchmarking.. Proceedings of the National Academy of Sciences of the United States of America. https://doi.org/10.1073/pnas.2509757122

Source records