List your company

Safety Evaluation on HADES-Dataset

43.67HADES ScoreQwen-VL-Max
-1.746810.044121.83533.6259Nov 30, 2024

Evaluation results

MethodLinks
Qwen-VL-MaxEvaluator=Llama-Guard-3-8B, System Prompt Setting=None2024.1143.6796.2296.5197.2395.49
GPT-4oEvaluator=Llama-Guard-3-8B, System Prompt Setting=None2024.112.6297.9697.8297.0997.53
GPT-4o-MiniEvaluator=Llama-Guard-3-8B, System Prompt Setting=None2024.112.6297.8297.2396.6594.76
Claude-3.5-SonnetEvaluator=Llama-Guard-3-8B, System Prompt Setting=None2024.11035.6642.0729.849.46