WhitzardNUWA Lab ↗
NUWANUWA INDEX

Search NUWA Index

Research · Benchmarks · Findings · Perspectives

中文
← Library

Institution

Apart Research

Roles and affiliations follow the cited source. A source check is not an independent replication.

More filters →

Apart Research ↗

Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities

QuestionHow sensitive are cyber-capability evaluations to elicitation and communication protocol?

Source summaryGPT-4o’s completion improved by 24.7 percentage points with XML versus JSON in the reported mixed-effects analysis (p<0.001).

NUWA research note · independent review pending

CybersecurityCapability