Benchmark Radar™
Star —

LexAgentHallu Benchmark

Explore score history ↗

LexAgentHallu is a hierarchical benchmark for profiling hallucinations in tool-augmented legal agents, containing 3414 instances across 17 legal categories and 6 task types, with dual-layer hallucination taxonomy and fine-grained metrics.

Released
2026-09-09
Evaluates
General AI, Language & Knowledge, cs.AI
Openness
unknown
Importer
Claire Radar
Review status
ai-name-audit-deferred

LexAgentHallu paper

No reported scores are on record for this benchmark yet.

Which sources cite LexAgentHallu?

Related General AI, Language & Knowledge, cs.AI benchmarks