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

Task-Oriented Dialogue on MultiWOZ 2.0 (test)

99.1Inform Rate

DarwinTOD

82.77287.01191.2595.489Jan 12, 2026Jan 18, 2026Jan 24, 2026Jan 30, 2026Feb 5, 2026Feb 11, 2026Feb 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
99.196.222.94120.59-
2026.01
99.196.222.94120.59-
2026.01
99.0595.8722.93120.39-
2026.01
98.6793.4522.08118.14-
2026.01
98.3492.8621.74117.34-
2026.01
98.3492.8621.74117.34-
2026.01
97.8591.0721.89116.35-
2026.01
97.6390.2821.55115.51-
2026.01
97.6390.2821.55115.51-
2026.01
97.2190.1421.23114.91-
2026.01
96.9289.1421.83114.86-
2026.01
96.9289.1421.83114.86-
2026.01
96.5790.1921.69115.07-
2026.01
95.480.717105.05-
2026.01
95.2788.9521.77113.88-
2026.01
94.8487.2121.97113-
2026.01
94.485.320.5110.35-
2026.01
93.984.720.2109.3-
2026.01
93.885.818.5108.3-
2026.01
92.279.318.57104.32-
2026.01
91.784.410.498.5-
2026.01
91.783.38.996.4-
2026.02
91.783.3--87
2026.01
90.4282.1718.96105.26-
2026.01
89.279.418.62102.92-
2026.02
88.978---
2026.02
88.384.6--91.4
2026.02
87.282.8--81.4
2026.01
85.572.916.5495.74-
2026.02
85.475.7---
2026.01
84.8874.9117.8997.79-
2026.02
84.785.9--90.7
2026.01
84.470.115.0192.26-
2026.02
84.470.1---
2026.02
83.969.9---
2026.01
83.8869.879.0985.97-
2026.02
83.470.3---