Agentic benchmark
CTI-REALM leaderboard
Every model the catalog carries a published CTI-REALM value for, ranked by that value.
CategoryAgentic
MeasureSuccess rate
TasksThreat-intelligence-to-detection-rule workflows
DifficultyProfessional cyber threat detection
Published byIntroducing Fugu-Cyber
A cybersecurity benchmark that measures whether an agent can turn raw threat-intelligence reports into working detection rules.
CTI-REALM ranking
1 model with a published CTI-REALM value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Success rate |
|---|---|---|---|
| 1 | SAFugu Cyber | Sakana AI | 72.1 |
Evidence key: Observed
Rows are ordered by the value Introducing Fugu-Cyber published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.