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

DROP

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reading ComprehensionDROP
DROP Accuracy92.28
138
Reading ComprehensionDROP
F1 Score92.2
96
Reading ComprehensionDROP (test)
F1 Score96.42
76
Reading ComprehensionDROP (dev)
F1 Score88.1
63
GenerationDROP
F1 Score48.74
49
Question AnsweringDROP
F1 Score87.5
45
Natural Language ReasoningDROP
Accuracy89.62
43
ReasoningDROP
Score89.27
42
Reading ComprehensionDROP
F1 Score86.2
35
Reading ComprehensionDROP (test)
F1 Score76
29
Reading ComprehensionDROP
DROP Score48.68
25
Discrete ReasoningDROP
Exact Match (EM)71.59
25
Reading ComprehensionDROP (test)
Accuracy90.8
23
Question AnsweringDROP MRQA out-of-domain evaluation
EM64.9
23
Video ReconstructionDrop
PSNR35.03
21
Reading ComprehensionDROP
DROP Score0.6733
20
Reading ComprehensionDROP
Loss0.4
20
Instruction-followingDROP
DROP Score51.53
20
Question AnsweringDROP nfl
F1 Score67.69
17
Reading ComprehensionDROP
Performance Score83.49
16
In-context retrievalDROP
Accuracy88.6
16
Question AnsweringDROP
Accuracy81.08
16
Multi-hop QADROP (test)
F1 Score87.9
14
Reading ComprehensionDROP MRQA out-of-domain
EM0.4884
14
Video Snapshot Compressive Imaging ReconstructionDrop
PSNR45.99
13
Showing 25 of 72 rows