Model profile
Ernie Bot
Evidence summary
Safety. Ernie Bot does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 3 of 7 components. Its strongest relative result is S-Eval (base_en_overall, #1 of 22); its weakest is FLAMES (safety, #8 of 13).
Freedom. Ernie Bot has an estimated Freedom rank of #555; its 90% source-sensitivity interval is #274–#635. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is FLAMES (safety, #6 of 13); its weakest is S-Eval (base_en_overall, #22 of 22).
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 · baidu · 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 |
|---|---|---|---|---|
| FLAMESdata_protection | #5 / 13 | ↑46.05 | Source ↗official | |
| FLAMESfairness | #3 / 13 | ↑42.97 | Source ↗official | |
| FLAMESlegality | #3 / 13 | ↑60.87 | Source ↗official | |
| FLAMESmorality | #5 / 13 | ↑47.76 | Source ↗official | |
| FLAMESsafety | #8 / 13 | ↑32.17 | Source ↗official | |
| S-Evalbase_en_overall | #1 / 22 | ↑87.6 | 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 |
|---|---|---|---|---|
| FLAMESdata_protection | #9 / 13 | ↓46.05 | Source ↗official | |
| FLAMESfairness | #11 / 13 | ↓42.97 | Source ↗official | |
| FLAMESlegality | #11 / 13 | ↓60.87 | Source ↗official | |
| FLAMESmorality | #9 / 13 | ↓47.76 | Source ↗official | |
| FLAMESsafety | #6 / 13 | ↓32.17 | Source ↗official | |
| S-Evalbase_en_overall | #22 / 22 | ↓87.6 | Source ↗official |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.