Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Travel Itinerary Retrieval and Ranking on Travel Itinerary 200 city-related queries (test)

89.5Top-5 Success Rate

CORE (Reasoning)

47.958.769.580.3Feb 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
89.583.576
2026.02
87.58275.5
2026.02
8680.573.5
2026.02
8579.572.5
2026.02
847871
2026.02
83.57871.5
2026.02
82.57669
2026.02
817568.5
2026.02
5544.530.5
2026.02
53.54330
2026.02
514128.5
2026.02
49.539.527