ELECTRAMarian

Reported on 4 benchmarks across 1 task

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

Natural Language Processing4 results

Code GenerationonCoNaLa
BLEU
30.18
best: 44.32 (PanGu-Coder-FT-I)
Code GenerationonCoNaLa
Exact Match Accuracy
10
best: 13.8 (RoBERTaMarian)
Code GenerationonDjango
Accuracy
65.32
best: 81.83 (MarianCG)
Code GenerationonDjango
BLEU Score
53.02
best: 90.41 (MarianCG)