Model profile
Wizardlm 7B
2023-04-23release date
1eval lineages
Evidence summary
Published evidence spans 1 evals and 3 of 7 behavior components. Its strongest relative result is SafetyBench (OFF, #16 of 21); its weakest is SafetyBench (UB, #21 of 21).
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 |
|---|---|---|---|---|---|
| SafetyBenchEM | #19 / 21 | 51.2 | ↑ higher | Source ↗official | |
| SafetyBenchIA | #20 / 21 | 55.4 | ↑ higher | Source ↗official | |
| SafetyBenchMH | #21 / 21 | 60.7 | ↑ higher | Source ↗official | |
| SafetyBenchOFF | #16 / 21 | 52.6 | ↑ higher | Source ↗official | |
| SafetyBenchPH | #19 / 21 | 52.4 | ↑ higher | Source ↗official | |
| SafetyBenchPP | #21 / 21 | 55.8 | ↑ higher | Source ↗official | |
| SafetyBenchUB | #21 / 21 | 48.8 | ↑ higher | Source ↗official |