List your company

Knowledge Graph Interaction Agent Task on KG

64.4Success RateClaude-Sonnet-4 Thinking
2.41618.50834.650.692Jul 8, 2026

Evaluation results

MethodLinks
Claude-Sonnet-4 ThinkingCategory=API LLMs, Variant=Thinking2026.0764.4
GPT-5Category=API LLMs2026.0764.1
Claude-Sonnet-4Category=API LLMs2026.0763.4
o3-miniCategory=API LLMs2026.0751.8
DeepSeek-R1Category=Open LLMs2026.0750.2
AgentLM-70BCategory=Open LLMs, Parameters=70B2026.0747
Qwen2.5-14B-InstructCategory=Open LLMs, Parameters=14B, Variant=Instruct2026.0735.3
Qwen2.5-32B-InstructCategory=Open LLMs, Parameters=32B, Variant=Instruct2026.0733.8
o4-miniCategory=API LLMs2026.0732.4
AgentRLCategory=RL Training2026.0730
EPPOCategory=RL Training2026.0729.6
AgentLM-13BCategory=Open LLMs, Parameters=13B2026.0726.8
Hephaestus-8B-IFTCategory=Open LLMs, Parameters=8B, Variant=IFT2026.0721.2
AgentLM-7BCategory=Open LLMs, Parameters=7B2026.0718.1
Hephaestus-8B-BaseCategory=Open LLMs, Parameters=8B, Variant=Base2026.0716
DeepSeek-V3Category=Open LLMs2026.0714
DCPOCategory=RL Training2026.0710.6
Qwen2.5-3B-InstructCategory=Open LLMs, Parameters=3B, Variant=Instruct2026.074.8
BAPOCategory=RL Training2026.074.8