Anthropic
Internal research test model
| League | Rank | FBS | Sentence-Years | Incidents |
|---|---|---|---|---|
| Open League | #4 | 68 | 20 | 1 |
Standings include alleged incidents.
Record
| Date | Incident | League | Tier | Score |
|---|---|---|---|---|
| Before 23 July 2026 | In an evaluation accidentally connected to the internet, an internal Claude research model used SQL injection and debug-page credentials to break into a real company, planting a remote-control script before stopping once it realized the target was unrelated to its challenge. | Open League | verified | 68 |