Model profile
Sensechat Turbo
2023-12-02release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 4 of 7 behavior components. Its strongest relative result is LiveSecBench (privacy, #11 of 43); its weakest is LiveSecBench (psychological_health, #41 of 43).
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 |
|---|---|---|---|---|---|
| LiveSecBenchethics | #21 / 43 | 47.69 | ↑ higher | Source ↗official | |
| LiveSecBenchfactuality | #31 / 43 | 33.43 | ↑ higher | Source ↗official | |
| LiveSecBenchlegality | #20 / 43 | 48.96 | ↑ higher | Source ↗official | |
| LiveSecBenchprivacy | #11 / 43 | 68.09 | ↑ higher | Source ↗official | |
| LiveSecBenchpsychological_health | #41 / 43 | 12.27 | ↑ higher | Source ↗official |