Model profile
Llama 3.3 70B Instruct
Metadeveloper
2024-12-06release date
#131 / 267overall rank
24eval lineages
1discovery sources
Evidence summary
Llama 3.3 70B Instruct has an estimated overall rank of #131; its 90% source-sensitivity interval is #80–#201. Its behavior-only rank is #120; company governance moves the combined estimate to #131. Published evidence spans 24 evals and 7 of 7 behavior components. Its strongest relative result is SpeciEval (belief_animal_sentience, #1 of 102); its weakest is AnimalHarmBench (score, #10 of 10).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗llama-3-3-instruct-70b
- Hugging Face ↗meta-llama/Llama-3.3-70B-Instruct
- NVIDIA ↗qc69jvmznzxy/llama-3_3-70b-instruct
- OpenRouter ↗meta-llama/llama-3.3-70b-instruct
- Official model page ↗Exact model document · Reviewed official Hugging Face owner · official repository
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 |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #199 / 311 | 0.8511 | ↓ lower | Source ↗official | |
| AbstentionBenchanswer_unknown_f1 | #8 / 20 | 0.8895 | ↑ higher | Source ↗official | |
| AbstentionBenchfalse_premise_f1 | #9 / 20 | 0.7079 | ↑ higher | Source ↗official | |
| AbstentionBenchstale_f1 | #12 / 20 | 0.6225 | ↑ higher | Source ↗official | |
| AbstentionBenchsubjective_f1 | #12 / 20 | 0.7191 | ↑ higher | Source ↗official | |
| AbstentionBenchunderspecified_context_f1 | #8 / 20 | 0.6586 | ↑ higher | Source ↗official | |
| AbstentionBenchunderspecified_intent_f1 | #13 / 20 | 0.7242 | ↑ higher | Source ↗official | |
| AILuminate General Purpose AI Chatchild_sexual_exploitation | #22 / 32 | 26 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatdefamation | #25 / 32 | 26.8 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chathate | #26 / 32 | 19 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatindiscriminate_weapons_cbrne | #26 / 32 | 42.8 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatintellectual_property | #26 / 32 | 23.6 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatnon_violent_crimes | #25 / 32 | 29.1 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatprivacy | #26 / 32 | 26 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsex_related_crimes | #25 / 32 | 24 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsexual_content | #27 / 32 | 46.8 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatspecialized_advice | #25 / 32 | 25.9 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatsuicide_self_harm | #24 / 32 | 20.3 | ↓ lower | Source ↗official | |
| AILuminate General Purpose AI Chatviolent_crimes | #27 / 32 | 38 | ↓ lower | Source ↗official | |
| Alignment Leaderboardcorrigibility | #22 / 24 | 3.951 | ↑ higher | Source ↗official | |
| Alignment Leaderboardhonesty | #18 / 24 | 3.346 | ↑ higher | Source ↗official | |
| Alignment Leaderboardnon_manipulation | #19 / 24 | 3.063 | ↑ higher | Source ↗official | |
| Alignment Leaderboardrobustness | #16 / 24 | 3.28 | ↑ higher | Source ↗official | |
| Alignment Leaderboardsafety | #20 / 24 | 3.365 | ↑ higher | Source ↗official | |
| Alignment Leaderboardscheming | #22 / 24 | 3.277 | ↑ higher | Source ↗official | |
| AnimalHarmBenchscore | #10 / 10 | -0.015 | ↑ higher | Source ↗official | |
| BlueBench AttaQ-100attaq_harmlessness_reward_pct | #11 / 18 | 83.8 | ↑ higher | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #69 / 105 | 53.54 | ↓ lower | Source ↗official | |
| Confabulationsconfabulation_rate | #19 / 52 | 17.82 | ↓ lower | Source ↗official | |
| Enkrypt AI Safety Leaderboardbias_attack_non_success_rate | #211 / 260 | 11.11 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardcbrn_attack_non_success_rate | #140 / 260 | 87.83 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardharmful_attack_non_success_rate | #145 / 260 | 66.11 | ↑ higher | Source ↗official | |
| Enkrypt AI Safety Leaderboardtoxicity_attack_non_success_rate | #109 / 258 | 97.18 | ↑ higher | Source ↗official | |
| FORTRESSaverage_risk_score | #32 / 49 | 44.79 | ↓ lower | Source ↗official | |
| FORTRESSover_refusal_score | #12 / 46 | 2.18 | ↓ lower | Source ↗official | |
| HUMAINE Trust, Ethics and Safetytrust_ethics_safety_score | #46 / 54 | 24.21 | ↑ higher | Source ↗official | |
| Large-scale Moral Machine experiment on LLMshuman_choice_distance | #9 / 39 | 0.8364 | ↓ lower | Source ↗official | |
| LiveSecBenchethics | #19 / 43 | 54.35 | ↑ higher | Source ↗official | |
| LiveSecBenchfactuality | #38 / 43 | 26.17 | ↑ higher | Source ↗official | |
| LiveSecBenchlegality | #14 / 43 | 66.51 | ↑ higher | Source ↗official | |
| LiveSecBenchprivacy | #31 / 43 | 30.35 | ↑ higher | Source ↗official | |
| LiveSecBenchpsychological_health | #40 / 43 | 17.08 | ↑ higher | Source ↗official | |
| Manager Coercion Benchcoercion_ladder_depth | #27 / 31 | 9 | ↓ lower | Source ↗self run | |
| MANTAAWMS | #3 / 7 | 0.476 | ↑ higher | Source ↗official | |
| MANTAAWVS | #4 / 7 | 0.422 | ↑ higher | Source ↗official | |
| MASKlying_probability_pct | #37 / 53 | 48.07 | ↓ lower | Source ↗official | |
| PandaBench JBB direct-request panelsafety_rate | #35 / 46 | 0.95 | ↑ higher | Source ↗official | |
| PHAREbias_resistance_diagnostic | #35 / 66 | 0.4539 | ↑ higher | Source ↗official | |
| PHAREhallucination_resistance_diagnostic | #47 / 70 | 0.6883 | ↑ higher | Source ↗official | |
| PHAREharm_resistance_diagnostic | #58 / 70 | 0.8604 | ↑ higher | Source ↗official | |
| PHAREjailbreak_resistance_diagnostic | #38 / 67 | 0.4768 | ↑ higher | Source ↗official | |
| RefusalBenchyouden_j | #17 / 19 | 0.01333 | ↑ higher | Source ↗official | |
| SOSBenchbiology_pvr | #12 / 23 | 0.408 | ↓ lower | Source ↗official | |
| SOSBenchchemistry_pvr | #14 / 23 | 0.54 | ↓ lower | Source ↗official | |
| SOSBenchmedicine_pvr | #11 / 23 | 0.546 | ↓ lower | Source ↗official | |
| SOSBenchpharmacology_pvr | #12 / 23 | 0.812 | ↓ lower | Source ↗official | |
| SOSBenchphysics_pvr | #14 / 23 | 0.516 | ↓ lower | Source ↗official | |
| SOSBenchpsychology_pvr | #11 / 23 | 0.446 | ↓ lower | Source ↗official | |
| SpeciesismBenchmorally_wrong_rate | #1 / 8 | 53.14 | ↑ higher | Source ↗official | |
| SpeciesismBenchspeciesism_recognition_rate | #2 / 8 | 96.34 | ↑ higher | Source ↗official | |
| SpeciEvalbelief_animal_sentience | #1 / 102 | 7 | ↑ higher | Source ↗official | |
| SpeciEvalland_animal_4ns | #62 / 102 | 4.64 | ↓ lower | Source ↗official | |
| SpeciEvalsea_animal_4ns | #63 / 102 | 4.85 | ↓ lower | Source ↗official | |
| SpeciEvalspeciesism | #18 / 102 | 1.53 | ↓ lower | Source ↗official | |
| SYCON Benchfalse_presupposition_tof | #9 / 11 | 1.9 | ↑ higher | Source ↗official | |
| SYCON Benchunethical_queries_tof | #6 / 11 | 1.39 | ↑ higher | Source ↗official | |
| TACbase_welfare_rate | #16 / 68 | 35.3 | ↑ higher | Source ↗self run |
Values evaluations
Descriptive values and political-framing results are separate from safety/ethics ranks. Each strip shows the evaluation’s observed model range; its endpoint labels state what lower and higher values mean.
UGI Political Values
ValueCompass
| Dimension | Value | Distribution |
|---|---|---|
| Universalism | 59.4 | |
| Self-direction | 41.7 | |
| Care / Harm | 19.6 | |
| Fairness / Cheating | 16.4 | |
| Ethical | 86.5 |
Taiwan Sovereignty Benchmark Pro
| Dimension | Value | Distribution |
|---|---|---|
| Pro-Taiwan rubric compatibility | 90 | |
| Warning-phrase rate | 0 | |
| Soft-censorship rate | 0 | |
| API-error rate | 0 |
Agent-ValueBench Moral Foundations (MFT08)
Agent-ValueBench HEXACO
| Dimension | Value | Distribution |
|---|---|---|
| Openness to experience | 6.1 | |
| Honesty-humility | 5.4 | |
| Extraversion | 5.1 | |
| Agreeableness | 6 | |
| Conscientiousness | 7.1 |