Model profile
DBRX Instruct
Evidence summary
Safety. DBRX Instruct has an estimated Safety rank of #323; its 90% source-sensitivity interval is #296–#326. Its behavior-only rank is #332; company governance moves the combined estimate to #323. Published Safety evidence spans 7 eval lineages and 5 of 7 components. Its strongest relative result is Enkrypt AI Safety Leaderboard (cbrn_attack_non_success_rate, #162 of 248); its weakest is HELM Safety (harmbench, #80 of 80).
Freedom. DBRX Instruct has an estimated Freedom rank of #23; its 90% source-sensitivity interval is #2–#132. Published Freedom evidence spans 6 eval lineages and 1 of 1 components. Its strongest relative result is HELM Safety (harmbench, #1 of 80); its weakest is HELM Safety (xstest, #79 of 80).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗databricks/dbrx-instruct
- OpenRouter ↗databricks/dbrx-instruct
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗direct research preview identity date
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 |
|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #80 / 80 | ↑0.254 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #195 / 248 | ↑11.89 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #162 / 248 | ↑85.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #226 / 248 | ↑34.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #200 / 246 | ↑91.23 | Source ↗official | |
| HELM Safetyanthropic_red_team | #80 / 80 | ↑0.766 | Source ↗official | |
| HELM Safetybbq | #67 / 80 | ↑0.792 | Source ↗official | |
| HELM Safetyharmbench | #80 / 80 | ↑0.271 | Source ↗official | |
| HELM Safetysimple_safety_tests | #80 / 80 | ↑0.535 | Source ↗official | |
| HELM Safetyxstest | #79 / 80 | ↑0.774 | 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 |
|---|---|---|---|---|
| AIRBench 2024 Safety Scenariossafety_scenarios | #1 / 80 | ↓0.254 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #85 / 248 | ↓85.17 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #22 / 248 | ↓34.44 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #46 / 246 | ↓91.23 | Source ↗official | |
| HELM Safetyanthropic_red_team | #1 / 80 | ↓0.766 | Source ↗official | |
| HELM Safetyharmbench | #1 / 80 | ↓0.271 | Source ↗official | |
| HELM Safetysimple_safety_tests | #1 / 80 | ↓0.535 | Source ↗official | |
| HELM Safetyxstest | #79 / 80 | ↑0.774 | Source ↗official |