Benchmark Radar™
Star —

WorkSurface-Bench

Explore score history ↗

WorkSurface-Bench evaluates enterprise agents on knowledge routing across documents, tables, and graphs. It includes 1,151 atomic tasks with auditable reference answers and scoring for route, evidence, answer, and efficiency.

Released
2026-07-28
Institutions
Peking University · University of Chinese Academy of Sciences
Evaluates
Factuality, General AI, Language & Knowledge, cs.CL
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

WorkSurface-Bench paper and code

No reported scores are on record for this benchmark yet.

Which sources cite WorkSurface-Bench?

Related Factuality, General AI, Language & Knowledge, cs.CL benchmarks