LLM Safety and Ethics Index

← All models

Developer

Meta

36 indexed models; 17 currently meet the evidence threshold for the overall ranking. Together they have results from 64 evaluations.

Official Meta model information ↗

Company governance evidence

Meta is represented at -1.25 SD relative to the matched Future of Life Institute edition. Provenance: Direct. This company-level evidence contributes 10% of overall model rank.

Models by Meta

ModelEvalsComponentsRankRelease date
Muse Spark 1.1117/7102026-07-09
Muse Spark33/7222026-04-08
Llama 3.3 70B Instruct247/71312024-12-06
Llama 2 7B Chat127/71402023-07-18
Llama 2 13B Chat86/71642023-07-18
Llama 4 Maverick287/71652025-04-05
Llama 3.1 405B Instruct226/71662024-07-23
Llama 3.2 Instruct 11B Vision34/7178—
Llama 3 8B Instruct157/71832024-04-18
Llama 3 70B Instruct137/71852024-04-18
Llama 3.1 70B Instruct197/71872024-07-23
Llama 2 70B Chat76/71922023-07-18
Llama 4 Scout167/72162025-04-05
Llama 3.1 8B Instruct257/72192024-07-23
Llama 3.2 90B Vision Instruct33/72282024-09-19
Llama 3.2 3B Instruct86/72502024-09-25
Llama 3.2 1B Instruct76/72532024-09-25
Llama 13B11/7—2023-02-24
Llama 3 1 405B Instruct Turbo13/7——
Llama 3 1 70B Instruct Turbo13/7——
Llama 3 70B Chat Hf13/7——
Llama 3 8B Chat Hf13/7——
Llama 3 8B Instruct Mopeymule13/7——
Llama 3 8B Instruct Rr13/7——
Llama 3.1 70B Base12/7—2024-07-23
Llama 3.1 8B Base12/7—2024-07-23
Llama 3.2 3B12/7——
Llama 3.2 90B Vision Instruct Turbo13/7——
Llama 30B11/7—2023-02-24
Llama 7B11/7—2023-02-24
Llama Nemotron Super 49B V1 511/7——
Opt 13B11/7—2022-05-11
Opt 175B11/7——
Opt 30B11/7—2022-05-11
Opt 6.7B11/7—2022-05-11
Opt 66B21/7—2022-06-23
Evaluations covering Meta models (64)

AA-Omniscience · AbstentionBench · Adversarial Robustness · Agent-SafetyBench · AgentDojo · AgentHarm · AILuminate General Purpose AI Chat · AIRBench 2024 Safety Scenarios · Alignment Leaderboard · AnimalHarmBench · Anthropic Agentic Misalignment — blackmail · Anthropic Agentic Misalignment — corporate espionage · BlueBench AttaQ-100 · BullshitBench v2 · CAIS Risk Index · CASE-Bench · ChineseSafe · Cisco AI Defense Rolling Single-Turn Leaderboard · Confabulations · Contextual MoralChoice · DecodingTrust · Do-Not-Answer · DSPSafeBench · DystopiaBench · Enkrypt AI Safety Leaderboard · FORTRESS · Gray Swan indirect prompt injection (15 attempts) · HarmBench · HELM Classic RealToxicityPrompts · HELM Safety · HUMAINE Trust, Ethics and Safety · JailBench · Large-scale Moral Machine experiment on LLMs · LiveSecBench · LLM Ethics Benchmark · MACHIAVELLI · Manager Coercion Bench · MANTA · MASK · Microsoft Phi Safety Panels · ODCV-Bench · Open LLM Safety Index · OR-Bench · PandaBench JBB direct-request panel · PHARE · PropensityBench · RefusalBench · S-Eval · SafeArena · SafetyBench · SALAD-Bench · Shell · SORRY-Bench · SOSBench · SpeciesismBench · SpeciEval · SYCON Bench · TAC · TrustLLM contemporary collapsed application · TukaBench · UAVBench safety-critical decision recognition · VETO Misfired Alignment · Vigil Mental Health Safety · XSTest