← Search

Table · dataset · 2026

CheatBench

Listed in Hugging Face Datasets

CheatBench Dataset Description Dataset

Description

Summary

CheatBench is a benchmark for evaluating monitors that detect reward hacking and cheating in agent traces. The dataset contains English-language trajectories from agent runs on existing benchmarks, including human-verified examples of cheating as well as vetted non-cheating traces. Each cheating trace is annotated with a category label describing the type of cheating behavior.

Read the rest (1 more)

CheatBench was created to… See the full description on the dataset page: huggingface.co/datasets/steinad/CheatBench.

Links

Where it is published

Catalogue records · 1

Topics

Stated by source
tabular · text · text classification
Provenance · 1 source records, 11 field assertions
SourceKeyLast seenRaw
Hugging Face Datasetssteinad/CheatBench15 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · Hugging Faceconnector:huggingface@1.0.0/gated
concepts[field].local:field:computer-science-aimapping · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].hf_modality:tabularsource · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].hf_modality:textsource · Hugging Faceconnector:huggingface@1.0.0
concepts[task].hf_task:text-classificationsource · Hugging Faceconnector:huggingface@1.0.0/tags[task_categories:*]
created_datesource · Hugging Faceconnector:huggingface@1.0.0
descriptionsource · Hugging Faceconnector:huggingface@1.0.0/description
licensesource · Hugging Faceconnector:huggingface@1.0.0/tags[license:*]
publication_datesource · Hugging Faceconnector:huggingface@1.0.0
titlesource · Hugging Faceconnector:huggingface@1.0.0/id
updated_datesource · Hugging Faceconnector:huggingface@1.0.0