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

PIQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense ReasoningPIQA
Accuracy94.9
757
Physical Commonsense ReasoningPIQA
Accuracy94.9
724
Question AnsweringPIQA
Accuracy86.5
589
Physical Interaction Question AnsweringPIQA
Accuracy94.9
462
Commonsense ReasoningPIQA
Accuracy89.99
400
ReasoningPIQA
Accuracy96.5
168
Physical Commonsense ReasoningPIQA (val)
Accuracy83
118
Zero-shot ReasoningPIQA
PIQA Zero-shot Accuracy82.54
115
Common Sense ReasoningPIQA
Accuracy91.89
100
Physical Commonsense ReasoningPIQA
Accuracy (PIQA)81.5
99
Physical ReasoningPIQA
Accuracy82.5
90
Physical Commonsense ReasoningPIQA
Accuracy85.91
85
Commonsense ReasoningPIQA (test)
Accuracy90.1
73
Physical Commonsense ReasoningPIQA (test)
Accuracy90.7
71
Multiple Choice Question AnsweringPIQA
Accuracy80.5
67
Commonsense reasoningPIQA 1.0 (test)
Accuracy82.21
64
Physical Commonsense ReasoningPIQA
Accuracy7,497
56
Physical Commonsense ReasoningPIQA
Accuracy82.54
51
Physical Commonsense ReasoningPiQA
Accuracy76.56
45
General Knowledge QAPIQA
Accuracy80
44
Commonsense ReasoningPIQA
Normalized Accuracy85.47
41
Question AnsweringPIQA (test)
Accuracy85
40
Physical Commonsense ReasoningPIQA
Accuracy (%)81.08
36
Question AnsweringPiQA
Accuracy81.77
36
Physical ReasoningPIQA
Accuracy91.3
34
Showing 25 of 101 rows