BAITBENCH

What is BAITBENCH?

Evaluates whether LLM agents exploit optional shortcuts in three synthetic tabular ML tasks to inflate public test scores while failing hidden tests.

Released

2026-08-31

Evaluates

Agents, Cybersecurity, Language & Knowledge

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.30724

BAITBENCH paper

• Paper https://arxiv.org/abs/2608.30724

Which sources cite BAITBENCH?

• BAITBENCH

Related Agents, Cybersecurity, Language & Knowledge benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActiveSciBench
• AdaMem-Bench