LongT5 XL

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical4 results

Language ModellingonSCROLLS
Avg.· 2021-12-15
42.53
best: 43.51 (CoLT5 XL)
SOTA
LongT5: Efficient Text-To-Text Transformer for Long Sequences arXiv:2112.07916
Language ModellingonSCROLLS
CNLI· 2021-12-15
88.2
best: 88.7 (UL2 20B)
SOTA
LongT5: Efficient Text-To-Text Transformer for Long Sequences arXiv:2112.07916
Language ModellingonSCROLLS
Nrtv· 2021-12-15
29.3
best: 31.1 (CoLT5 XL)
SOTA
LongT5: Efficient Text-To-Text Transformer for Long Sequences arXiv:2112.07916
Language ModellingonSCROLLS
Qspr· 2021-12-15
53.1
best: 53.9 (CoLT5 XL)
SOTA
LongT5: Efficient Text-To-Text Transformer for Long Sequences arXiv:2112.07916