List your company

Safety Moderation on Harmbench

87.2F1 ScoreQwen3Guard-8B-Gen-strict
68.27273.18678.183.014Dec 5, 2025Dec 25, 2025Jan 14, 2026Feb 3, 2026Feb 23, 2026Mar 15, 2026Apr 5, 2026

Evaluation results

MethodLinks
Qwen3Guard-8B-Gen-strictStreaming=no, Moderation Policy=Gen-strict, Backbone Scale=8B2026.0487.2
Qwen3Guard-4B-Gen-strictStreaming=no, Moderation Policy=Gen-strict, Backbone Scale=4B2026.0486.7
BingoGuardParameter Count=8B2025.1286.4
WildGuardParameter Count=7B2025.1286.2
WildguardSize=7B2026.0386
Roblox Guard 1.0Parameter Count=8B2025.1285.7
Llama-Guard-3Size=8B2026.0385
Qwen3Guard-Stream-8B-strictStreaming=yes, Moderation Policy=strict, Backbone Scale=8B2026.0485
LlamaGuard3Parameter Count=8B2025.1284.9
ShieldGemmaParameter Count=7B2025.1284.8
Qwen3Guard-Stream-8B-looseStreaming=yes, Moderation Policy=loose, Backbone Scale=8B2026.0484.7
Qwen3Guard-Stream-4B-strictStreaming=yes, Moderation Policy=strict, Backbone Scale=4B2026.0484.3
Qwen3Guard-Stream-4B-looseStreaming=yes, Moderation Policy=loose, Backbone Scale=4B2026.0483.6
GPT-4o2025.1283.5
Llama3-StreamGuard-8BStreaming=yes, Backbone Scale=8B2026.0483.3
Llama3-StreamGuard-3BStreaming=yes, Backbone Scale=3B2026.0483.2
Qwen3Guard-Stream-0.6B-strictStreaming=yes, Moderation Policy=strict, Backbone Scale=0.6B2026.0483.1
Llama3-StreamGuard-1BStreaming=yes, Backbone Scale=1B2026.0482.4
MD-JudgeSize=7B2026.0381
Qwen3Guard-Stream-0.6B-looseStreaming=yes, Moderation Policy=loose, Backbone Scale=0.6B2026.0480.6
NemoGuardParameter Count=8B2025.1278.6
FanarGuardSize=4B2026.0377
PolyGuard-MinistralSize=8B2026.0376
PolyGuard-QwenSize=7B2026.0375
PolyGuard-SmolSize=0.5B2026.0372
ShieldGemma-2bSize=2B2026.0369