Skip to content

Models/model

OpenAI o-series

OpenAI's o1, o3, and o4 reasoning models.

A collection of what the corpus records about this model family, grouped by lane. It is not a capability assessment.

Defense & research

Aug 19, 2025

MCPTox benchmarks tool poisoning across 45 live MCP servers and 20 LLM agents

DefenseBenchmarkarXiv

Jul 14, 2025

Microsoft's ExCyTIn-Bench evaluates LLM agents on multi-step threat investigation over Sentinel logs

DefenseBenchmarkMicrosoft

May 21, 2025

BountyBench measures AI agents on detect, exploit and patch tasks from real bug bounties

DefenseBenchmarkStanford University, UC Berkeley

May 7, 2025

UC Santa Cruz study integrates LLM agents into CAGE 4 and finds RL defenders still outperform them

DefensePaperUC Santa Cruz

Findings drawing on these records

Jul 28, 2025

More capable models are not reliably more robust to prompt injection, and some are more susceptible.

Corroboratedmeasured3 evidence records

Apr 1, 2025

Text in an MCP tool's description can steer an agent's other actions, including leaking local secrets.

Corroboratedmeasured2 evidence records

Jul 14, 2025

LLM agents fall well short of reliable performance on realistic threat-investigation and threat-hunting benchmarks built from security logs.

Corroboratedmeasured3 evidence records

May 7, 2025

In the CAGE 4 simulation, reinforcement-learning defenders outperformed LLM-based defenders.

Revalidatemeasured1 evidence record