WorkSurface-Bench

What is WorkSurface-Bench?

WorkSurface-Bench evaluates enterprise agents on knowledge routing across documents, tables, and graphs. It includes 1,151 atomic tasks with auditable…

Released

2026-07-28

Evaluates

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

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.25765

WorkSurface-Bench paper and code

• Paper https://arxiv.org/abs/2607.25765
• Code https://github.com/haolpku/WorkSurface-Bench

Which sources cite WorkSurface-Bench?

• WorkSurface-Bench

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

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench