Benchmark Radar™
Star —

FinCUABuildBench

Explore score history ↗

Evaluates construction of dynamic financial computer-using agent (CUA) tasks across 576 requests spanning 24 workflows and runtime variations, with qualification based on execution tests and quality checks.

Released
2026-09-07
Institutions
Northeastern University · Wuhan University · Mohamed bin Zayed University of Artificial Intelligence
Evaluates
Agents & Tool Use, Finance, cs.AI
Openness
unknown
Importer
Claire Radar
Review status
ai-reviewed

FinCUABuildBench paper and code

No reported scores are on record for this benchmark yet.

Which sources cite FinCUABuildBench?

Related Agents & Tool Use, Finance, cs.AI benchmarks