List your company

Task-oriented Plan Retrieval on Travel Itinerary Single-turn

95Pass RateIn-context
22.241.16078.9Mar 1, 2026

Evaluation results

MethodLinks
In-contextModel=Gemini 3 Flash, Scorer=–2026.039512,846
Semantic XPathModel=GPT-5 mini, Scorer=Entail2026.03855,161
Semantic XPathModel=GPT-5 mini, Scorer=Sem2026.03755,548
Semantic XPathModel=Gemini 3 Flash, Scorer=Entail2026.03755,240
Semantic XPathModel=Gemini 3 Flash, Scorer=Sem2026.03655,454
In-contextModel=GPT-5 mini, Scorer=–2026.035512,136
Flat RAGModel=Gemini 3 Flash, Scorer=–2026.03353,349
Flat RAGModel=GPT-5 mini, Scorer=–2026.03253,137