List your company

Question Answering on BBQ (ambiguous)

95Accuracygpt-5-thinking
87.7289.6191.593.39Dec 19, 2025

Evaluation results

MethodLinks
gpt-5-thinkingweb search=with web search2025.1295
OpenAI o3web search=with web search2025.1294
gpt-5-thinkingweb search=without web search2025.1293
gpt-5-mainweb search=without browse2025.1293
GPT-4oweb search=without browse2025.1288