Model profile
Llama 3.1 Tulu 3 8B Sft
2024-11-18release date
2eval lineages
Evidence summary
Published evidence spans 2 evals and 5 of 7 behavior components. Its strongest relative result is Enkrypt AI Safety Leaderboard (harmful_attack_non_success_rate, #72 of 260); its weakest is AbstentionBench (underspecified_context_f1, #20 of 20).
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-SFT
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
- Release source ↗repository created at proxy
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 |
|---|---|---|---|---|---|
| AbstentionBenchanswer_unknown_f1 | #14 / 20 | 0.8605 | ↑ higher | Source ↗official | |
| AbstentionBenchfalse_premise_f1 | #18 / 20 | 0.6112 | ↑ higher | Source ↗official | |
| AbstentionBenchstale_f1 | #11 / 20 | 0.632 | ↑ higher | Source ↗official | |
| AbstentionBenchsubjective_f1 | #11 / 20 | 0.7244 | ↑ higher | Source ↗official | |
| AbstentionBenchunderspecified_context_f1 | #20 / 20 | 0.3572 | ↑ higher | Source ↗official | |
| AbstentionBenchunderspecified_intent_f1 | #11 / 20 | 0.7311 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #227 / 260 | 9.82 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #125 / 260 | 88.5 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #72 / 260 | 86.11 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #99 / 258 | 97.45 | ↑ higher | Source ↗official |