Data Science @ Uni Vienna
banner
ds-vienna.bsky.social
Data Science @ Uni Vienna
@ds-vienna.bsky.social
Our research network is a hub for all #DataScience activities @univie.ac.at #univienna

https://datascience.univie.ac.at
How capable are coding agents in advancing research? A new benchmark, REXBench, evaluates large language model-based agents and their potential to produce reliable code. It presents results from testing nine recent agents, and addresses issues of data contamination #LargeLanguageModels
October 13, 2025 at 10:20 AM
😋🍫
August 7, 2025 at 7:37 AM
Reposted by Data Science @ Uni Vienna