RH-Detect Benchmark

What is RH-Detect?

Reward hacking, where a model exploits an evaluation signal without completing the intended task, threatens the reliability of deployed language model systems.

Released

2026-10-07

Evaluates

General AI, Vision & 3D, cs.LG

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2610.10947

RH-Detect paper

• Paper https://arxiv.org/abs/2610.10947

Which sources cite RH-Detect?

• RH-Detect

Related General AI, Vision & 3D, cs.LG benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A Real-World CAD Segmentation Benchmark
• A3S-Bench
• AARRI-Bench