SentinelBench

What is SentinelBench?

SentinelBench is an open-source benchmark for time-evolving monitoring tasks. It contains 100 tasks across 10 synthetic web environments (email, calendars…

Released

2026-06-03

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.05342

SentinelBench paper

• Paper https://arxiv.org/abs/2606.05342

Which sources cite SentinelBench?

• SentinelBench

Related General AI, Language & Knowledge, cs.AI 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