Sign inGet started
Paper · arXiv

FrontierChallenge: Evaluating Scientific Workflow Completion

Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated programs, or a single domain. We introduce FrontierChallenge, a cross-domain benchmark comprising 300 end-to-end scientific workflows. In this paper, we release and evaluate 97 of these tasks, spanning quantum chemistry, molecular dynamics, materials characterization, analytical chemistry, life science, and electrochemistry/environment. Each task provides fixed inputs and specifies a bundle of required scientific deliverables. We evaluate twelve frontier models with three agent scaffolds. Pass Rate measures the fraction of tasks satisfying the fu...

AuthorsLiangcai Su, Zhaopeng Feng, Zhuo Chen et al.
Primary categorycs.AI
Published25 August 2026
Last updated at source9 September 2026
cs.AIcs.CLcs.SE
Embed this entry
<iframe src="https://silytics.si/embed/item/515fbd1b-2d5a-4d5b-91e2-04c7afb50441" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Connected in the knowledge graph

Explore this entry in the graph

Models and datasets referencing this paper

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.