Model profile
Wizardlm 2 8x22B
Evidence summary
Safety. Wizardlm 2 8x22B does not meet the evidence gate for a Safety rank. Published Safety evidence spans 2 eval lineages and 3 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #33 of 248); its weakest is AgentDrive Safety Compliance (scr, #38 of 48).
Freedom. Wizardlm 2 8x22B has an estimated Freedom rank of #525; its 90% source-sensitivity interval is #372–#640. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #88 of 248); its weakest is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #215 of 248).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗microsoft/WizardLM-2-8x22B
- OpenRouter ↗microsoft/wizardlm-2-8x22b
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AgentDrive Safety Compliancescr | #38 / 48 | ↑57.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #163 / 248 | ↑13.18 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #33 / 248 | ↑93.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #159 / 248 | ↑57.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #128 / 246 | ↑96.18 | Source ↗official |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #215 / 248 | ↓93.5 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #88 / 248 | ↓57.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #119 / 246 | ↓96.18 | Source ↗official |