Model profile
Llama 3.1 Tulu 3 8B
Ai2developer
2024-11-20release date
#40 / 267overall rank
3eval lineages
Evidence summary
Llama 3.1 Tulu 3 8B has an estimated overall rank of #40; its 90% source-sensitivity interval is #9–#207. Its behavior-only rank is #38; company governance moves the combined estimate to #40. Published evidence spans 3 evals and 5 of 7 behavior 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, #218 of 260).
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
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 |
|---|---|---|---|---|---|
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #8 / 32 | 11.1 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #6 / 32 | 7.2 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chathate | #6 / 32 | 2.6 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #10 / 32 | 14.8 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #10 / 32 | 8.1 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #7 / 32 | 7.2 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #6 / 32 | 5.8 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #8 / 32 | 8 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #14 / 32 | 20.6 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #10 / 32 | 11.2 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #10 / 32 | 9.7 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #6 / 32 | 9.8 | ↓ lower | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #218 / 260 | 10.85 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #54 / 260 | 92 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #87 / 260 | 82.78 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #70 / 258 | 98.18 | ↑ higher | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #1 / 46 | 1 | ↑ higher | Source ↗official |