List your company

Malicious Action Detection on tau-Bench retail (test)

7.8TPRGPT-OSS-Safeguard 20B
-0.3121.7943.96.006Oct 3, 2025

Evaluation results

MethodLinks
GPT-OSS-Safeguard 20B2025.107.851.8
AprielGuard2025.104.36.3
Granite-Guardian 3.3-8B2025.1000.9
Qwen-3-Guard2025.1000.2