List your company

Utility Evaluation on AgentDojo

78.4UtilityGLM-4.5
5.18424.19243.262.208Sep 26, 2025

Evaluation results

MethodLinks
GLM-4.5Prompt=InjecPrompt, Technique=default2025.0978.4
GLM-4.5Prompt=Multi-turn, Technique=default2025.0975.8
Kimi-K2Prompt=Multi-turn, Technique=default2025.0972
Kimi-K2Prompt=InjecPrompt, Technique=default2025.0971.5
Kimi-K2Prompt=Multi-turn, Technique=ChatInject2025.0969.9
GLM-4.5Prompt=InjecPrompt, Technique=ChatInject + tool2025.0968.1
GLM-4.5Prompt=InjecPrompt, Technique=ChatInject2025.0967.9
GLM-4.5Prompt=Multi-turn, Technique=ChatInject2025.0967.9
GLM-4.5Prompt=InjecPrompt, Technique=ChatInject + think2025.0965.7
Qwen-3Prompt=Multi-turn, Technique=default2025.0952.4
Qwen-3Prompt=InjecPrompt, Technique=default2025.0950.9
Grok-2Prompt=InjecPrompt, Technique=default2025.0941.7
GPT-ossPrompt=Multi-turn, Technique=default2025.0938.3
Kimi-K2Prompt=InjecPrompt, Technique=ChatInject + tool2025.0935.2
Kimi-K2Prompt=InjecPrompt, Technique=ChatInject2025.0935
Grok-2Prompt=Multi-turn, Technique=default2025.0933.9
Grok-2Prompt=Multi-turn, Technique=ChatInject2025.0931.9
Grok-2Prompt=InjecPrompt, Technique=ChatInject2025.0929.8
Qwen-3Prompt=InjecPrompt, Technique=ChatInject2025.0928.3
Qwen-3Prompt=Multi-turn, Technique=ChatInject2025.0927.5
Qwen-3Prompt=InjecPrompt, Technique=ChatInject + think2025.0924.4
Qwen-3Prompt=InjecPrompt, Technique=ChatInject + tool2025.0922.9
GPT-ossPrompt=InjecPrompt, Technique=default2025.0919.6
GPT-ossPrompt=InjecPrompt, Technique=ChatInject2025.0918.8
Llama-4Prompt=Multi-turn, Technique=default2025.0918.5
Llama-4Prompt=InjecPrompt, Technique=default2025.0916.5
Llama-4Prompt=Multi-turn, Technique=ChatInject2025.0916.2
Llama-4Prompt=InjecPrompt, Technique=ChatInject2025.0915.9
Llama-4Prompt=InjecPrompt, Technique=ChatInject + tool2025.0914.7
GPT-ossPrompt=InjecPrompt, Technique=ChatInject + think2025.0911.1
GPT-ossPrompt=InjecPrompt, Technique=ChatInject + tool2025.099
GPT-ossPrompt=Multi-turn, Technique=ChatInject2025.098