Model profile
OLMo 2 13B Instruct
Evidence summary
Safety. OLMo 2 13B Instruct has an estimated Safety rank of #300; its 90% source-sensitivity interval is #31–#332. Its behavior-only rank is #305; company governance moves the combined estimate to #300. Published Safety evidence spans 6 eval lineages and 5 of 7 components. Its strongest relative result is AILuminate General Purpose AI Chat (sex_related_crimes, #7 of 32); its weakest is HELM Safety (anthropic_red_team, #76 of 80).
Freedom. OLMo 2 13B Instruct has an estimated Freedom rank of #195; its 90% source-sensitivity interval is #45–#544. Published Freedom evidence spans 5 eval lineages and 1 of 1 components. Its strongest relative result is HELM Safety (anthropic_red_team, #5 of 80); its weakest is AILuminate General Purpose AI Chat (sex_related_crimes, #26 of 32).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗allenai/OLMo-2-1124-13B-Instruct
- 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 |
|---|---|---|---|---|
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #12 / 32 | ↓14.2 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #11 / 32 | ↓11 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #19 / 32 | ↓10.7 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #18 / 32 | ↓25 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #11 / 32 | ↓8.2 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #10 / 32 | ↓9.3 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #11 / 32 | ↓8.6 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #7 / 32 | ↓7.5 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #11 / 32 | ↓17.5 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #11 / 32 | ↓13.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #9 / 32 | ↓8.5 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #9 / 32 | ↓12 | Source ↗official | |
| HELM Safetyanthropic_red_team | #76 / 80 | ↑0.907 | Source ↗official | |
| HELM Safetybbq | #75 / 80 | ↑0.704 | Source ↗official | |
| HELM Safetyharmbench | #69 / 80 | ↑0.519 | Source ↗official | |
| HELM Safetysimple_safety_tests | #76 / 80 | ↑0.81 | Source ↗official | |
| HELM Safetyxstest | #64 / 80 | ↑0.926 | 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 |
|---|---|---|---|---|
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #21 / 32 | ↑14.2 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #22 / 32 | ↑11 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #14 / 32 | ↑10.7 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #15 / 32 | ↑25 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #21 / 32 | ↑8.2 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #23 / 32 | ↑9.3 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #22 / 32 | ↑8.6 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #26 / 32 | ↑7.5 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #22 / 32 | ↑17.5 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #22 / 32 | ↑13.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #24 / 32 | ↑8.5 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #23 / 32 | ↑12 | Source ↗official | |
| HELM Safetyanthropic_red_team | #5 / 80 | ↓0.907 | Source ↗official | |
| HELM Safetyharmbench | #12 / 80 | ↓0.519 | Source ↗official | |
| HELM Safetysimple_safety_tests | #5 / 80 | ↓0.81 | Source ↗official | |
| HELM Safetyxstest | #64 / 80 | ↑0.926 | Source ↗official |