70
CyberSecEvalTest
📈
Evaluate LLMs' cybersecurity risks and capabilities
Safety & Security
-
-
meta-llama/Llama-Guard-3-8B
Text Generation • 8B • Updated • 291k • • 240 -
meta-llama/Prompt-Guard-86M
Text Classification • 0.3B • Updated • 57.9k • • 279 -
17
Prompt Injection Detection Benchmark
📝Check for prompt injection in text
-
protectai/deberta-v3-base-prompt-injection-v2
Text Classification • 0.2B • Updated • 257k • • 77 -
94
LLM Safety Leaderboard
🥇Explore and submit LLM benchmarks
fdtn-ai/Foundation-Sec-8B
Text Generation • 8B • Updated • 8.91k • • 265Note Foundational Base Model Released by Cisco for SOC operations and other cyber ops.
-
nvidia/llama-3.1-nemoguard-8b-content-safety
Text Classification • Updated • 1.5k • 29 -
meta-llama/Llama-Guard-4-12B
Image-Text-to-Text • 12B • Updated • 37.2k • • 61 -
facebook/Meta-SecAlign-8B
Updated • 1.61k • 10 -
Qwen/Qwen3Guard-Gen-8B
Text Generation • 8B • Updated • 30.8k • 61 -
Qwen/Qwen3Guard-Stream-8B
Feature Extraction • 8B • Updated • 442 • 27 -
openai/gpt-oss-safeguard-20b
Text Generation • 22B • Updated • 4.41k • • 103