List your company

Tool-use Question Answering on ToolQA Easy 1.0

90Yelp AccReact
0.5623.784770.22Dec 3, 2025

Evaluation results

MethodLinks
ReactAgent Approach=React, Model=gpt-oss-120b2025.129017767378
ReflexionAgent Approach=Reflexion, Model=gpt-oss-120b2025.12877487380
ReactAgent Approach=React, Model=Qwen3-32B2025.12769548572
ReactAgent Approach=React, Model=Qwen3-14B2025.12718497667
RP-ReActAgent Approach=RP-ReAct, Model=Qwen3-32B2025.12687436978
RP-ReActAgent Approach=RP-ReAct, Model=Qwen3-14B2025.12615377265
RP-ReActAgent Approach=RP-ReAct, Model=gpt-oss-120b2025.12539508978
ReflexionAgent Approach=Reflexion, Model=Qwen3-14B2025.12432233049
ReflexionAgent Approach=Reflexion, Model=Qwen3-32B2025.12394432874
RP-ReActAgent Approach=RP-ReAct, Model=DeepSeek-8B2025.1230002028
RP-ReActAgent Approach=RP-ReAct, Model=gpt-oss-20b2025.1226794843
React-100Agent Approach=React-100, Model=gpt-oss-20b2025.1222412187
ReActAgent Approach=ReAct, Model=DeepSeek-8B2025.121700339
ReactAgent Approach=React, Model=gpt-oss-20b2025.1215411115
ReActAgent Approach=ReAct, Model=DeepSeek-7B2025.121100421
RP-ReActAgent Approach=RP-ReAct, Model=DeepSeek-7B2025.12110046
ReflexionAgent Approach=Reflexion, Model=gpt-oss-20b2025.1245498