HANDBOOK.md Benchmark

What is HANDBOOK.md?

HANDBOOK.md evaluates whether tool-using agents consistently obey lengthy standing procedures while completing workplace tasks in self-contained company…

Released

2026-07-28

Evaluates

Biology & Drug Discovery, Finance, Language & Knowledge, Logistics & Operations, Long Context

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.25398

HANDBOOK.md paper and code

• Paper https://arxiv.org/abs/2607.25398
• Code https://github.com/surge-ai/handbook

Which sources cite HANDBOOK.md?

• HANDBOOK.md

Related Biology & Drug Discovery, Finance, Language & Knowledge, Logistics & Operations, Long Context benchmarks

• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• ActiveSciBench
• Ada-LEval
• AdaMem-Bench
• AdvancedMathBench