Lumina
CTI-REALM leaderboard
1 ranked models · higher is better · labels show rank and score
View accessible chart data
| Model | Rank | Provider | Score |
|---|---|---|---|
| Fugu Cyber | #1 | Sakana AI | 72.1% |
Loading benchmark header
Loading benchmark registry
Agents · Benchmark profile
A cybersecurity benchmark that measures whether an agent can turn raw threat-intelligence reports into working detection rules.
Data verified 27 Jul 2026 · Methodology 1.8.0
1 ranked models · higher is better · labels show rank and score
| Model | Rank | Provider | Score |
|---|---|---|---|
| Fugu Cyber | #1 | Sakana AI | 72.1% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Fugu Cyber sakana-fugu-cyber | Sakana AI | closed | Estimated reference | 72.1% |
About CTI-REALM
A cybersecurity benchmark that measures whether an agent can turn raw threat-intelligence reports into working detection rules. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
A cybersecurity benchmark that measures whether an agent can turn raw threat-intelligence reports into working detection rules.
Fugu Cyber by Sakana AI currently leads with 72.1%.
1 model in the LuminaBench cohort have a qualifying score on this benchmark.
Related