65
CyberSecEvalTest
📈
Evaluate LLM cybersecurity risks
Security
-
-
meta-llama/Llama-Guard-3-8B
Text Generation • Updated • 310k • • 192 -
meta-llama/Prompt-Guard-86M
Text Classification • Updated • 38.4k • 251 -
16
Prompt Injection Detection Benchmark
📝detect prompt injection risks
-
protectai/deberta-v3-base-prompt-injection-v2
Text Classification • Updated • 206k • • 52 -
91
LLM Safety Leaderboard
🥇View and submit machine learning model evaluations
-
fdtn-ai/Foundation-Sec-8B
Text Generation • Updated • 18k • 94