CC Capabilities

Capabilities / Vendor framing

gpt-oss-safeguard technical report

OpenAI Cybersecurity score 36/100 confidence 0.9
Category
Vendor framing
Capability
Vendor platform capability signal
Observed
2025-10-29
Thesis section
Appendix III, section two: vendor threshold and platform capability evidence

Claim

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order to label content under that policy. In this report, we describe gpt-oss-safeguard’s capabilities and provide our baseline safety evaluations on the gpt-oss-safeguard models, using.

Oracle verdict

This is a low-signal vendor radar item. Keep it as context only unless a later benchmark, deployment, procurement change, or labour-market datapoint turns it into direct Appendix III evidence.

Why it matters

Imported from the official OpenAI release stream because it was published on or after the GPT-5 launch date (2025-08-07).

Custom GPT Ask the Oracle