@misc{re-bench,
  title = {RE-Bench: Evaluating frontier AI R\&D capabilities of language model agents against human experts},
  url = {https://arxiv.org/abs/2411.15114v2},
  author = {Hjalmar Wijk and Tao Lin and Joel Becker and Sami Jawhar and Neev Parikh and Thomas Broadley and Lawrence Chan and Michael Chen and Josh Clymer and Jai Dhyani and Elena Ericheva and Katharyn Garcia and Brian Goodrich and Nikola Jurkovic and Holden Karnofsky and Megan Kinniment and Aron Lajko and Seraphina Nix and Lucas Sato and William Saunders and Maksym Taran and Ben West and Elizabeth Barnes},
  year = {2024},
  date = {2024-11-22},
  version = {arXiv:2411.15114v2},
  note = {arXiv:2411.15114v2}
}

@misc{re-bench-nuwa,
  title = {RE-Bench: Evaluating frontier AI R\&D capabilities of language model agents against human experts — NUWA research record},
  url = {https://whitzard.tech/nuwa/whitzard-index/work/re-bench/},
  version = {2026-10-29.1},
  organization = {NUWA Frontier AI Safety Lab},
  howpublished = {Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--re-bench.json},
  note = {NUWA research note. Source-reading scope and independent review status are stated on the record. Snapshot 2026-10-29.1. Retained note edition: https://whitzard.tech/nuwa/whitzard-index/data/record-editions/2026-10-29.1--re-bench.json.}
}