Model profile
Mixtral 8X22B Instruct
Mistral AIdeveloper
2024-04-17release date
#237 / 267overall rank
9eval lineages
Evidence summary
Mixtral 8X22B Instruct has an estimated overall rank of #237; its 90% source-sensitivity interval is #48–#260. Its behavior-only rank is #231; company governance moves the combined estimate to #237. Published evidence spans 9 evals and 5 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #83 of 260); its weakest is Qwen2 Safety Panel (illegal, #3 of 3).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- OpenRouter ↗mistralai/mixtral-8x22b-instruct
- Official model documentation ↗Family-level model document · mistral · 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 |
|---|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #71 / 80 | 0.44 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #203 / 260 | 11.89 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #83 / 260 | 90.67 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #185 / 260 | 53.89 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #99 / 258 | 97.45 | ↑ higher | Source ↗official | |
| FORTRESSaverage_risk_score | #41 / 49 | 56.06 | ↓ lower | Source ↗official | |
| FORTRESSover_refusal_score | #16 / 46 | 2.77 | ↓ lower | Source ↗official | |
| HELM Safetyanthropic_red_team | #70 / 80 | 0.962 | ↑ higher | Source ↗official | |
| HELM Safetybbq | #52 / 80 | 0.916 | ↑ higher | Source ↗official | |
| HELM Safetyharmbench | #68 / 80 | 0.521 | ↑ higher | Source ↗official | |
| HELM Safetysimple_safety_tests | #74 / 80 | 0.915 | ↑ higher | Source ↗official | |
| HELM Safetyxstest | #55 / 80 | 0.941 | ↑ higher | Source ↗official | |
| Qwen2 Safety Panelfraud | #3 / 3 | 8.49 | ↓ lower | Source ↗official | |
| Qwen2 Safety Panelillegal | #3 / 3 | 6.87 | ↓ lower | Source ↗official | |
| Qwen2 Safety Panelpornography | #3 / 3 | 33.82 | ↓ lower | Source ↗official | |
| Qwen2 Safety Panelprivacy | #3 / 3 | 15.03 | ↓ lower | Source ↗official |