CoQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CoQA
60PR-AUC
16
CoQA
79.19Accuracy
14
CoQA
47.2PRR (AlignScore)
14
CoQA (dev)
96.52AUARC (Token Entropy)
14
CoQA (dev)
77.8AUROC (Token Entropy)
14
CoQA (dev)
0.849Overall F1
14
CoQA
100Recall
12
COQA
86.5AIBC
12
CoQA
92.4Exact Match (EM)
11
CoQA
1.253Overall Score
10
CoQA
80.53F1 Score (CoQA)
10
CoQA
62.65F1 Score
10
CoQA (val)
63.65EM
9
CoQA (val)
68.35Distinct-1
9
CoQA (dev)
84.09Distinct-1
9
CoQA
0.265PRR
8
CoQA (val)
67.83EM
8
CoQA
60.3EM
8
CoQA
84F1 Score (CoQA)
7
CoQA (test)
87AUROC
7
CoQA zero-shot (test)
73F1 Score
6
CoQA (val test)
73F1
6
CoQA (dev)
85F1 Score
6
CoQA without human rewrites v1.0 (test)
83.4Overall F1
6
CoQA (val)
32.1F1 Score
5