List your company

Task-oriented Plan Retrieval on To Do List Single-turn

84Pass RateSemantic XPath
38.2450.126273.88Mar 1, 2026

Evaluation results

MethodLinks
Semantic XPathModel=GPT-5 mini, Scorer=Entail2026.03845,184
In-contextModel=GPT-5 mini, Scorer=–2026.03805,444
In-contextModel=Gemini 3 Flash, Scorer=–2026.037210,465
Semantic XPathModel=Gemini 3 Flash, Scorer=Entail2026.03725,605
Semantic XPathModel=Gemini 3 Flash, Scorer=Sem2026.03685,710
Semantic XPathModel=GPT-5 mini, Scorer=Sem2026.03645,937
Flat RAGModel=Gemini 3 Flash, Scorer=–2026.03482,934
Flat RAGModel=GPT-5 mini, Scorer=–2026.03402,722