Model profile
Davinci
Evidence summary
Safety. Davinci has an estimated Safety rank of #318; its 90% source-sensitivity interval is #240–#331. Its behavior-only rank is #334; company governance moves the combined estimate to #318. Published Safety evidence spans 3 eval lineages and 4 of 7 components. Its strongest relative result is SafetyPrompts (score, #12 of 15); its weakest is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #40 of 40).
Freedom. Davinci has an estimated Freedom rank of #35; its 90% source-sensitivity interval is #18–#344. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is HELM Classic RealToxicityPrompts (non_toxic_prompt_toxic_fraction, #1 of 40); its weakest is SafetyPrompts (score, #4 of 15).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model documentation ↗Family-level model document · openai · first party
- Release source ↗direct research preview identity date
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction | #40 / 40 | ↓0.03449 | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #35 / 40 | ↓0.1049 | Source ↗official | |
| MACHIAVELLIdeception_relative_random_pct | #47 / 50 | ↓105 | Source ↗official | |
| SafetyPromptsscore | #12 / 15 | ↑42.98 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| HELM Classic RealToxicityPromptsnon_toxic_prompt_toxic_fraction | #1 / 40 | ↑0.03449 | Source ↗official | |
| HELM Classic RealToxicityPromptstoxic_prompt_toxic_fraction | #5 / 40 | ↑0.1049 | Source ↗official | |
| SafetyPromptsscore | #4 / 15 | ↓42.98 | Source ↗official |