LLM Safety and Ethics Index

← All models

Developer

Mistral AI

38 indexed models; 18 currently meet the evidence threshold for the overall ranking. Together they have results from 47 evaluations.

Official Mistral AI model information ↗

Company governance evidence

Mistral AI is represented at -1.21 SD relative to the matched Future of Life Institute edition. Provenance: Direct. This company-level evidence contributes 10% of overall model rank.

Models by Mistral AI

ModelEvalsComponentsRankRelease date
Mistral Large66/7772024-02-26
Mistral Medium45/71262023-12-11
Magistral Medium66/71542025-06-10
Mistral Small 3.142/71712025-03-11
Mistral 7B Instruct217/72052023-09-27
Mistral Small 3.235/72072025-06-19
Mistral Medium 3.156/72092025-08-12
Mistral Nemo45/72142024-07-18
Mistral Medium 343/72152025-05-07
Mistral Small 444/72172026-01-23
Mistral Medium 3.534/72352026-03-31
Mixtral 8X22B Instruct95/72372024-04-17
Mistral Small 386/72392025-01-30
Mistral Large 396/72472025-12-01
Magistral Small35/72522025-06-04
Mixtral 8X7B Instruct106/72602023-12-10
Mistral Large 2115/72622024-07-24
Magistral Small 250934/72672025-09-12
Devstral11/7——
Devstral 222/7——
Devstral Small11/7——
Devstral Small 211/7——
Devstral Small 250511/7—2025-05-12
Ministral 3 14B22/7—2025-10-31
Ministral 3 3B22/7—2025-10-31
Ministral 3 8B22/7—2025-10-31
Ministral 3B 251211/7——
Ministral 8B 24.1014/7—2024-10-16
Ministral 8B 24.10 Moderated14/7—2024-10-16
Mistral 7B13/7——
Mistral 7B Instruct V0.2 Eai Aligned13/7——
Mistral Large 2402 Moderated14/7—2024-02-26
Mistral Large Latest13/7——
Mistral Nemo Minitron 8B Instruct13/7——
Mistral Small23/7——
Mistral Small 211/7——
Mistral Small Latest13/7——
Voxtral Small 24B 250711/7——
Evaluations covering Mistral AI models (47)

AA-Omniscience · AbstentionBench · Adversarial Robustness · AgentHarm · AILuminate General Purpose AI Chat · AIRBench 2024 Safety Scenarios · Alignment Leaderboard · AnimalHarmBench · BlueBench AttaQ-100 · BullshitBench v2 · CASE-Bench · ChineseSafe · Cisco AI Defense Rolling Single-Turn Leaderboard · Confabulations · Contextual MoralChoice · DSPSafeBench · DystopiaBench · Emergent Collusion · Enkrypt AI Safety Leaderboard · FlagEval Safety and Values · FORTRESS · HarmBench · HELM Safety · HUMAINE Trust, Ethics and Safety · JailBench · Large-scale Moral Machine experiment on LLMs · LiveSecBench · MANTA · MASK · Microsoft Phi Safety Panels · OR-Bench · PacifAIst · PHARE · Qwen2 Safety Panel · RefusalBench · S-Eval · SafeDialBench · SALAD-Bench · Shell · SM-Bench · SORRY-Bench · SpeciEval · SuperCLUE Safety · TAC · UAVBench safety-critical decision recognition · VETO Misfired Alignment · XSTest