Benchmark Radar™
Star —

CatchBench

Explore score history ↗

Assesses agent failure auditing across PRE, LIVE, and POST information states with seven task contracts covering evidential and Gold-derived diagnostics.

Released
2026-08-24
Institutions
University of Southern California
Evaluates
Agents, General AI, Language & Knowledge
Openness
unknown
Importer
Claire Radar
Review status
ai-reviewed

CatchBench paper and code

No reported scores are on record for this benchmark yet.

Which sources cite CatchBench?

Related Agents, General AI, Language & Knowledge benchmarks