Model profile
Llama 7B
2023-02-24release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is MACHIAVELLI (deception_relative_random_pct, #47 of 50); its weakest is MACHIAVELLI (deception_relative_random_pct, #47 of 50).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Official model page ↗Family-level model document · meta · first party
- 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 |
|---|---|---|---|---|---|
| MACHIAVELLIdeception_relative_random_pct | #47 / 50 | 105 | ↓ lower | Source ↗official |