Model profile
Pangu Pro Moe 72B A16B
1eval lineages
Evidence summary
Published evidence spans 1 evals and 4 of 7 behavior components. Its strongest relative result is LiveSecBench (psychological_health, #33 of 43); its weakest is LiveSecBench (privacy, #43 of 43).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Release source ↗unresolved
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 |
|---|---|---|---|---|---|
| LiveSecBenchethics | #42 / 43 | 9.51 | ↑ higher | Source ↗official | |
| LiveSecBenchfactuality | #42 / 43 | 16.5 | ↑ higher | Source ↗official | |
| LiveSecBenchlegality | #40 / 43 | 12.05 | ↑ higher | Source ↗official | |
| LiveSecBenchprivacy | #43 / 43 | 5.84 | ↑ higher | Source ↗official | |
| LiveSecBenchpsychological_health | #33 / 43 | 27.71 | ↑ higher | Source ↗official |