Model profile
GPT Oss Safeguard 20B
OpenAIdeveloper
2025-10-29release date
#91 / 309overall rank
4eval lineages
Evidence summary
GPT Oss Safeguard 20B has an estimated overall rank of #91; its 90% source-sensitivity interval is #29–#188. Its behavior-only rank is #104; company governance moves the combined estimate to #91. Published evidence spans 4 evals and 5 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #59 of 241); its weakest is DystopiaBench (laguardia_score, #39 of 50).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗openai/gpt-oss-safeguard-20b
- OpenRouter ↗openai/gpt-oss-safeguard-20b
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #31 / 104 | ↓17.55 | Source ↗official | |
| DystopiaBenchbasaglia_score | #36 / 50 | ↓68.63 | Source ↗official | |
| DystopiaBenchbaudrillard_score | #34 / 50 | ↓64.37 | Source ↗official | |
| DystopiaBenchhuxley_score | #26 / 50 | ↓72 | Source ↗official | |
| DystopiaBenchlaguardia_score | #39 / 50 | ↓69.4 | Source ↗official | |
| DystopiaBenchorwell_score | #35 / 50 | ↓73.53 | Source ↗official | |
| DystopiaBenchpetrov_score | #29 / 50 | ↓73.6 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #59 / 241 | ↑25.58 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #187 / 241 | ↑82 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #103 / 241 | ↑74.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #104 / 239 | ↑96.91 | Source ↗official | |
| TACbase_welfare_rate | #33 / 76 | ↑28.21 | Source ↗self run |