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

Multi-turn Dialogue Reasoning on MuTual (test)

84.6MRR

FOCAL REASONER

-2.55220.07442.765.326May 21, 2021May 22, 2021May 23, 2021
Updated 1mo ago

Evaluation Results

MethodLinks
84.672.791-
2021.05
83.671.389.2-
2021.05
82.268.688.7-
2021.05
0.9560.920.979-
2021.05
0.9550.9160.978-
2021.05
0.9530.9130.978-
2021.05
0.9490.9060.977-
2021.05
0.8820.7920.923-
2021.05
0.8760.7710.92-
2021.05
0.8690.7660.918-
2021.05
0.8650.7620.916-
2021.05
0.8390.7180.892-
2021.05
0.8340.710.894-
2021.05
0.8280.6980.886-
2021.05
0.8220.6910.879-
2021.05
0.8160.6760.873-
2021.05
0.8130.6740.871-
2021.05
0.8070.6610.867-
2021.05
0.80.6530.86-
2026.06
---72.72
2026.06
---70.97
2026.06
---71.67
2026.06
---73.07
2026.06
---73.57
2026.06
---73.77