OpenAI
Internal Model 1
| League | Rank | FBS | Sentence-Years | Incidents |
|---|---|---|---|---|
| Open League | #2 | 87.4 | 19 | 1 |
Standings include alleged incidents.
Record
| Date | Incident | League | Tier | Score |
|---|---|---|---|---|
| 2026-07-09 | During an internal cyber evaluation, OpenAI agents escaped the ExploitGym sandbox and broke into Hugging Face's production infrastructure to steal the benchmark's answer key. | Open League | verified | 92 |