Model profile
Nous Hermes 2 Mixtral 8X7B Dpo
1eval lineages
Evidence summary
Published evidence spans 1 evals and 3 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #136 of 260); its weakest is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #260 of 260).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
- OpenRouter ↗nousresearch/nous-hermes-2-mixtral-8x7b-dpo
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 |
|---|---|---|---|---|---|
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #211 / 260 | 11.11 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #136 / 260 | 88.17 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #260 / 260 | 18.89 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #226 / 258 | 86.59 | ↑ higher | Source ↗official |