List your company

Tool-calling on τ-Bench (test)

43.77TSRQwen 2.5 7B (SFT)
21.763627.476833.1938.9032Oct 3, 2025

Evaluation results

MethodLinks
Qwen 2.5 7B (SFT)Defense=None, Stage=SFT, Poison=5%, Threat Model=TM32025.1043.77100
Qwen 2.5 7B (SFT) + Llama-firewallDefense=Llama-firewall (LF), Stage=SFT, Poison=5%, Threat Model=TM32025.1043.19100
Qwen 2.5 7B (SFT) + Granite GuardianDefense=Granite Guardian 3.3-8B (GG), Stage=SFT, Poison=5%, Threat Model=TM32025.1042.61100
Qwen 2.5 7B (Base)Defense=None, Stage=Base, Poison=0%2025.1022.61—