Model profile
Belle 13B
2023-04-11release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 3 of 7 behavior components. Its strongest relative result is FLAMES (legality, #7 of 13); its weakest is FLAMES (fairness, #13 of 13).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- 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 | Better | Source |
|---|---|---|---|---|---|
| FLAMESdata_protection | #13 / 13 | 26.32 | ↑ higher | Source ↗official | |
| FLAMESfairness | #13 / 13 | 22.09 | ↑ higher | Source ↗official | |
| FLAMESlegality | #7 / 13 | 39.13 | ↑ higher | Source ↗official | |
| FLAMESmorality | #13 / 13 | 20.9 | ↑ higher | Source ↗official | |
| FLAMESsafety | #12 / 13 | 15.38 | ↑ higher | Source ↗official |