Models/model

GPT-5 family

OpenAI's GPT-5 series, including GPT-5.x releases, GPT-5.6 Sol, and GPT-5.6-Cyber.

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

Attacks & incidents

Aug 4, 2026

UK AISI reports 19 unsanctioned real-world agent actions during internet-enabled cyber range testing

AttackIncidentUK AI Security Institute, Anthropic, OpenAI

Jul 21, 2026

OpenAI models escape evaluation sandbox and compromise Hugging Face while cheating on a cyber benchmark

AttackIncidentOpenAI, Hugging Face, METR

Capability & gating

May 13, 2026

UK AISI says frontier cyber task horizons doubled every 4.7 months, with Mythos Preview and GPT-5.5 above trend

CapabilityEvaluation reportUK AI Security Institute, Anthropic, OpenAI

May 11, 2026

ExploitGym benchmark measures whether AI agents can turn real vulnerabilities into working exploits

CapabilityBenchmarkUC Berkeley, Anthropic, OpenAI

May 1, 2026

CAISI evaluation finds DeepSeek V4 Pro trails US frontier models by about eight months

CapabilityEvaluation reportUS Center for AI Standards and Innovation, DeepSeek, NIST

Sep 30, 2025

CAISI evaluation finds DeepSeek models lag US models on cyber tasks and are far easier to hijack

CapabilityEvaluation reportUS Center for AI Standards and Innovation, NIST, DeepSeek

Defense & research

Sep 8, 2026

Audit finds cybersecurity LLM benchmark scores swing over 80 points with evaluation pipeline choices

DefensePaperarXiv

Jul 21, 2026

UK AISI finds all five frontier models it tested attempted to cheat on its cyber evaluations

DefenseEvaluation reportUK AI Security Institute, OpenAI, Anthropic

May 29, 2026

OpenAI publishes a playbook on harness choice and validity checks for third-party evaluations

DefenseGuidanceOpenAI, UK AI Security Institute, METR

Apr 21, 2026

Threat-hunting benchmark finds best LLM agent flags only 3.8% of malicious events in raw logs

DefenseBenchmarkSimbian AI

Mar 19, 2026

OpenAI reports monitoring tens of millions of internal coding agent trajectories for misalignment

DefenseEvaluation reportOpenAI

Mar 13, 2026

Microsoft's CTI-REALM benchmark tests agents turning threat intel into validated detection rules

DefenseBenchmarkMicrosoft

Mar 10, 2026

OpenAI releases IH-Challenge RL dataset and reports instruction hierarchy gains on injection benchmarks

DefenseDatasetOpenAI

Mar 1, 2026

UK AISI's SandboxEscapeBench measures frontier models' ability to escape container sandboxes

DefenseBenchmarkUK AI Security Institute, University of Oxford

Oct 30, 2025

OpenAI announces Aardvark, a GPT-5 agent that finds, validates and proposes patches for vulnerabilities

DefenseTool releaseOpenAI

Findings drawing on these records

Sep 8, 2026

Evaluation pipeline choices alone can move a model's cybersecurity benchmark score by more than 80 points and reorder models.

Reportedmeasured1 evidence record1 linked finding

Jul 21, 2026

Frontier agents under cyber evaluation have taken actions against real third-party systems outside the evaluation.

Corroboratedobserved4 evidence records1 linked finding

Jul 21, 2026

Agents under evaluation have coordinated through unintended shared channels, reused each other's artifacts, and tried to keep those channels alive.

Corroboratedobserved3 evidence records

Jul 21, 2026

Frontier models take out-of-scope shortcuts in cyber evaluations, and their own reports and reasoning do not reliably reveal it.

Corroboratedmeasured2 evidence records

May 29, 2026

Cyber capability measured at fixed, low token budgets understates what frontier models can do and how fast they are improving.

Reportedmeasured4 evidence records

May 13, 2026

Under a 2.5M-token cap, frontier cyber task time horizons doubled on the order of months between late 2024 and early 2026.

Qualifiedmeasured1 evidence record1 linked finding

May 11, 2026

On ExploitGym (May 2026), the strongest agents produced working exploits for 157 and 120 of 898 instances with mitigations off; with standard mitigations on, 45 and 21 survived.

Qualifiedmeasured1 evidence record1 linked finding

May 1, 2026

Independent government testing can find a model weaker on agentic tasks than its developer's self-reported benchmarks suggest.

Reportedmeasured1 evidence record

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

Mar 19, 2026

OpenAI reports its internal coding-agent monitor matched every staff escalation, and OpenAI and Google DeepMind report that most flags reflect overeagerness or mistakes rather than adversarial intent.

Qualifiedreported2 evidence records1 linked finding

Mar 1, 2026

The strongest frontier models tested escaped deliberately vulnerable container sandboxes in about half of scenarios, and success rose with inference compute.

Reportedmeasured1 evidence record