iiRecord
Agentic AI Atlas · CyberBench
benchmark:cyber-bencha5c.ai
II.
Benchmark overview

benchmark:cyber-bench

Reference · live

CyberBench overview

CyberBench (Princeton et al.) measures language-model and agent capability on real-world cybersecurity capture-the-flag tasks spanning crypto, web, reverse engineering, pwn, and forensics.

BenchmarkOutgoing · 2Incoming · 1

Attributes

displayName
CyberBench
homepageUrl
kind
security
targetsKind
AgentVersion
description
CyberBench (Princeton et al.) measures language-model and agent capability on real-world cybersecurity capture-the-flag tasks spanning crypto, web, reverse engineering, pwn, and forensics.

Outgoing edges

applies_to2

Incoming edges

bounds_subject1