Share your thoughts, 1 month free Claude Pro on usSee more

Knowledge Graph navigation on AgentBench KG

72.7Task Completion Score (TCS)

GPT-5-mini

Updated 6d ago

Evaluation Results

Method	Links
GPT-5-mini 2026.05		72.7
Gemini-3-flash 2026.05		44
DeepSeek-V3.2 2026.05		34
Qwen3-235B-A22B 2026.05		31.3