AI Safety Evidence

← All models

Developer

Alibaba

106 indexed models; 52 currently meet the evidence threshold for the overall ranking. Together they have results from 87 evaluations.

Official Alibaba model information ↗

Company governance evidence

Alibaba is represented at -1.01 SD relative to the matched Future of Life Institute edition. Provenance: Direct. This company-level evidence contributes 10% of overall model rank.

Models by Alibaba

ModelEvalsComponentsRankRelease date
Qwen3.5 27B66/7522026-02-24
Qwen3.5 397B A17B97/7532026-02-16
Qwen 72B Chat44/7632023-11-30
Qwen3 235B A22B Fp8 Throughput63/7662025-04-28
Qwen2 72B Instruct105/7672024-06-07
Qwen3 Max76/7722025-09-24
Qwen3.5 9B45/7822026-02-27
Qwen3.6 27B45/7842026-04-21
Qwen3.6 Max Preview43/7872026-04-22
Qwen3 4B45/7882025-04-27
Qwen3.7 Max86/7912026-05-20
Qwen3 235B A22B297/71072025-04-29
Qwen2.5 72B Instruct197/71102024-09-16
Qwen 14B Chat84/71182023-09-25
Qwen3.6 Plus76/71212026-04-02
Qwen3.8 Max55/71242026-08-03
Qwen3 32B87/71282025-04-29
Qwen3 Next 80B A3B116/71312025-09-11
Qwen3.7 Plus55/71352026-05-26
Qwen3.5 Plus55/71392026-02-15
Qwen2.5 32B Instruct55/71402024-09-19
Qwen1.5 32B Chat46/71462024-04-02
Qwen3 Max Preview32/71492025-09-05
Qwen1.5 14B Chat65/71512024-02-04
Qwen3 30B A3B Instruct76/71582025-07-28
Qwen3 235B A22B Instruct 250734/71612025-07-21
Qwen1.5 72B Chat136/71632024-02-04
Qwen3 Coder 480B A35B Instruct42/71752025-07-22
Qwen1.5 7B Chat96/71802024-02-04
Qwen3 30B A3B55/72092025-04-27
Qwen 7B Chat94/72112023-08-03
Qwen3.5 4B35/72122026-02-27
Qwen3.5 122B A10B55/72182026-02-24
Qwen 2.5 7B Instruct207/72222024-09-19
Qwen3.5 35B A3B54/72252026-02-24
Qwen 2.5 14B Instruct65/72312024-09-19
Qwen3.5 Flash 02 2333/7243—
Qwen3 14B56/72452025-04-27
Qwen2 7B Instruct54/72502024-06-07
Qwen 2.5 Max46/72522025-01-25
Qwen2.5 3B Instruct33/72582024-09-17
Qwen 2.5 1.5B Instruct53/72602024-09-19
Qwen1.5 0.5B Chat34/72622024-02-04
Qwen3 8B106/72672025-04-29
Qwen3 Next 80B A3B Instruct32/72692025-09-09
Qwen2.5 7B33/7270—
Qwen3 Vl 235B A22B Instruct44/72812025-09-22
Qwq 32B45/72862025-03-06
Qwen 1.8B Chat33/72902023-11-30
Qwen3 Vl 8B Instruct33/72932025-10-11
Qwen1.5 1.8B Chat45/72992024-02-04
Qwen 2.5 0.5B Instruct43/73032024-09-19
Chatplug 13B11/7——
Chatplug 3.7B11/7—2023-04-19
Qwen 2 Vl 72B Instruct23/7—2024-09-17
Qwen Plus23/7——
Qwen Turbo11/7——
Qwen1.5 110B Chat24/7—2024-04-25
Qwen1.5 4B Chat24/7—2024-02-04
Qwen2 0.5B Instruct11/7—2024-06-03
Qwen2 1.5B Instruct21/7—2024-06-07
Qwen2 5 7B Instruct 1M13/7——
Qwen2 57B A14B Instruct13/7——
Qwen2 7B11/7——
Qwen2 7B Chat11/7—2024-06-07
Qwen2.5 14B Instruct 1M13/7——
Qwen2.5 Coder 0.5B Instruct11/7—2024-11-06
Qwen2.5 Coder 1.5B Instruct11/7—2024-09-18
Qwen2.5 Coder 3B Instruct11/7—2024-11-06
Qwen2.5 Math 1.5B Instruct11/7—2024-09-16
Qwen3 0.6B21/7—2025-04-27
Qwen3 0.6B Instruct11/7——
Qwen3 1.7B11/7—2025-04-27
Qwen3 1.7B Instruct11/7——
Qwen3 14B Instruct11/7——
Qwen3 235B A22B Instruct11/7——
Qwen3 30B A3B 250722/7——
Qwen3 32B Instruct11/7——
Qwen3 4B 2507 Instruct22/7——
Qwen3 4B Instruct11/7—2025-04-29
Qwen3 4B Thinking 250711/7—2025-08-05
Qwen3 8B Base11/7——
Qwen3 8B Instruct11/7——
Qwen3 Coder 30B A3B Instruct22/7—2025-07-31
Qwen3 Coder Next11/7—2026-01-30
Qwen3 Omni 30B A3B11/7——
Qwen3 Omni 30B A3B Instruct11/7—2025-09-20
Qwen3 Vl 235B A22B22/7—2025-09-22
Qwen3 Vl 30B A3B22/7—2025-09-30
Qwen3 Vl 30B A3B Instruct22/7—2025-09-30
Qwen3 Vl 32B22/7——
Qwen3 Vl 32B Instruct22/7—2025-10-19
Qwen3 Vl 4B11/7——
Qwen3 Vl 4B Instruct11/7—2025-10-11
Qwen3 Vl 8B22/7—2025-10-11
Qwen3.512/7—2026-02-16
Qwen3.5 0 8B11/7—2026-02-28
Qwen3.5 2B11/7—2026-02-28
Qwen3.5 Flash22/7——
Qwen3.5 Max11/7——
Qwen3.5 Omni Flash11/7——
Qwen3.5 Omni Plus11/7——
Qwen3.6 35B A3B11/7—2026-04-15
Qwen3.6 Flash00/7——
Qwen3.7 Flash21/7——
Qwq 32B Preview13/7——
Evaluations covering Alibaba models (87)

AA-Omniscience · AbstentionBench · Agent-SafetyBench · AgentDrive Safety Compliance · AILuminate General Purpose AI Chat · AIRBench 2024 Safety Scenarios · Alignment Leaderboard · Anthropic Agentic Misalignment — blackmail · Anthropic Agentic Misalignment — corporate espionage · Arena Factuality — Text Arena (factuality-only weighting) · AuAu Authoritarian Response Audit · BrokenMath · BullshitBench v2 · CASE-Bench · ChineseSafe · ChiSafetyBench · Cisco AI Defense Rolling Single-Turn Leaderboard · CMoralEval · COMPL-AI AI-Identity Disclosure · COMPL-AI LLM RuLES Multi-Turn Rule Following · COMPL-AI TensorTrust Goal-Hijacking Resistance · Confabulations · Contextual MoralChoice · CRiskEval · CValues · DSPSafeBench · DystopiaBench · Emergent Collusion · Enkrypt AI Safety Leaderboard · Fake Alignment (FINE) · FinEval 6.0 Safety Awareness · FinEval Financial Security Knowledge · FlagEval Safety and Values · FLAMES · FORTRESS · Governance Decay under Passive Context Compaction · HalluVerse-M3 Hallucination Recognition · HarmBench · HarmVideoBench · HELM Safety · HUMAINE Trust, Ethics and Safety · HyperCLOVA X Toxic Continuation Panels · IndoBias-Pairs — parity-aware culturally grounded bias · Inkling-Small model card — FORTRESS · Inkling-Small model card — StrongREJECT · JailBench · JuICE Cultural-Error Span Detection · KIDBench Implicit Child Cue · LiveSecBench · M3-SafetyBench · Manager Coercion Bench · MASK · MT-JailBench CrescendoX · MuPPET Contextual Privacy · ODCV-Bench · Open LLM Safety Index · OR-Bench · PacifAIst · PandaBench JBB direct-request panel · PHARE · Pokee-Isaac model card — DTAP · PropensityBench · Qwen2 Safety Panel · RefusalBench · S-Eval · SABER · SafeArena · SafeDialBench · SafetyBench · SALAD-Bench · Shell · SM-Bench · Social Welfare Function Benchmark · SORRY-Bench · SOSBench · SpeciesismBench · SpeciEval · StereoTales Harmful Associations · SuperCLUE Safety · SYCON Bench · TAC · ThaiSafetyBench · ToolPrivacyBench · TrustLLM contemporary collapsed application · UAVBench safety-critical decision recognition · Vectara HHEM Factual Consistency · VETO Misfired Alignment