List your company

Shallow Retrieval on MultiWOZ 2.2

98Vanilla APAVanilla
39.96855.03470.185.166Apr 27, 2026

Evaluation results

MethodLinks
VanillaModel Pair (Architect / Executive)=DeepSeek Reasoner / V3.22026.0498———
VanillaModel Pair (Architect / Executive)=GPT 5.4 / 5.4 mini2026.0470.9———
VanillaModel Pair (Architect / Executive)=Gemini 3.1 Pro / 2.5 Flash2026.0464———
VanillaModel Pair (Architect / Executive)=Claude Sonnet 4.6 / Haiku 4.52026.0442.2———
SSRPModel Pair (Architect / Executive)=Gemini 3.1 Pro / 2.5 Flash2026.04—80.926.411.52
SSRPModel Pair (Architect / Executive)=Claude Sonnet 4.6 / Haiku 4.52026.04—43.94.035.35
SSRPModel Pair (Architect / Executive)=DeepSeek Reasoner / V3.22026.04—991.022.51
SSRPModel Pair (Architect / Executive)=GPT 5.4 / 5.4 mini2026.04—87.523.414.2