ChurnBench

What is ChurnBench?

Measures staleness errors in agentic AI answers under temporal drift across heterogeneous enterprise data sources.

Released

2026-09-10

Evaluates

Code & Software, General AI, cs.SE

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.11515

ChurnBench paper and code

• Paper https://arxiv.org/abs/2609.11515
• Code https://github.com/vsingh45/churnbench

Which sources cite ChurnBench?

• ChurnBench

Related Code & Software, General AI, cs.SE benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• Active-SWE
• ActiveSciBench