Model profile
Llama 3.1 Tulu 3 8B
Evidence summary
Safety. Llama 3.1 Tulu 3 8B has an estimated Safety rank of #63; its 90% source-sensitivity interval is #11–#239. Its behavior-only rank is #58; company governance moves the combined estimate to #63. Published Safety evidence spans 3 eval lineages and 5 of 7 components. Its strongest relative result is PandaBench JBB direct-request panel (safety_rate, #1 of 46); its weakest is Enkrypt AI Safety Leaderboard (bias_attack_non_success_rate, #228 of 270).
Freedom. Llama 3.1 Tulu 3 8B has an estimated Freedom rank of #606; its 90% source-sensitivity interval is #427–#645. Published Freedom evidence spans 3 eval lineages and 1 of 1 components. Its strongest relative result is AILuminate General Purpose AI Chat (sexual_content, #19 of 32); its weakest is AILuminate General Purpose AI Chat (defamation, #27 of 32).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Hugging Face ↗allenai/Llama-3.1-Tulu-3-8B
- 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 |
|---|---|---|---|---|
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #8 / 32 | ↓11.1 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #6 / 32 | ↓7.2 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #6 / 32 | ↓2.6 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #10 / 32 | ↓14.8 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #10 / 32 | ↓8.1 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #7 / 32 | ↓7.2 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #6 / 32 | ↓5.8 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #8 / 32 | ↓8 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #14 / 32 | ↓20.6 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #10 / 32 | ↓11.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #10 / 32 | ↓9.7 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #6 / 32 | ↓9.8 | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #228 / 270 | ↑10.85 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #47 / 270 | ↑92 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #105 / 270 | ↑82.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #63 / 268 | ↑98.18 | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #1 / 46 | ↑1 | 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 | #25 / 32 | ↑11.1 | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #27 / 32 | ↑7.2 | Source ↗official | |
| AILuminate General Purpose AI Chathate | #27 / 32 | ↑2.6 | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #23 / 32 | ↑14.8 | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #23 / 32 | ↑8.1 | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #26 / 32 | ↑7.2 | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #27 / 32 | ↑5.8 | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #25 / 32 | ↑8 | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #19 / 32 | ↑20.6 | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #23 / 32 | ↑11.2 | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #22 / 32 | ↑9.7 | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #27 / 32 | ↑9.8 | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #221 / 270 | ↓92 | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #166 / 270 | ↓82.78 | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #201 / 268 | ↓98.18 | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #35 / 46 | ↓1 | Source ↗official |