ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

Ziru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang +15 more
2/12/2026

No official code found. Best implementation: OSU-NLP-Group/ScienceAgentBench (136 stars, MIT, last commit 2026-04-29).

Semantic Scholar

Code Implementations(1)

OSU-NLP-Group/ScienceAgentBenchCommunity78%
MIT

[ICLR'25] ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery

13619Shell, PythonOct 2, 20245 months agoMIT
ai4sciencebioinformaticschemoinformaticscode-generationcognitive-neuroscience+4 more

Cite this paper

@article{chen2026scienceagentbench,
  title  = {ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery},
  author = {Ziru Chen and Shijie Chen and Yuting Ning and Qianheng Zhang and Boshi Wang and Botao Yu and Yifei Li and Zeyi Liao and Chen Wei and Zitong Lu and Vishal Dey and Mingyi Xue and Frazier N. Baker and Benjamin Burns and Daniel Adu-Ampratwum and Xuhui Huang and Xia Ning and Song Gao and Yu Su and Huan Sun},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:f15f2fa356b48abd7689f3f6ab7889ef22eca3a8},
  journal = {ICLR 2025 2025}
}

Discussion