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

MIC

Benchmarks

Task NameDataset NameSOTA ResultTrend
Rule-of-Thumb GenerationMIC (test)
R-155.18
27
Tabular ClassificationMIC (test)
Accuracy98.23
18
Multiclass ClassificationMIC TabArena v0.1 (test)
LogLoss0.438
10
Value AlignmentMIC (test)
Align Score5.48
10
Open-ended conversationMIC (in-domain)
ROUGE-L23.98
8
Image CompressionMIC (test)
CPU Encoding Latency (s)7.78
5
Rule-of-Thumb GenerationMIC
Well-formedness0.568
3
Showing 7 of 7 rows