Benchmark Radar™
Star —

DeCompBench

Explore score history ↗

DeCompBench evaluates agent safety against decomposition attacks, where harmful tasks are broken into benign subtasks; it measures refusal rates and objective fulfillment on decomposed variants.

Released
2026-06-12
Institutions
Carnegie Mellon University · University of California, Berkeley
Evaluates
Agents, General AI, Safety, Safety & Trustworthiness
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

DeCompBench paper and dataset

No reported scores are on record for this benchmark yet.

Which sources cite DeCompBench?

Related Agents, General AI, Safety, Safety & Trustworthiness benchmarks