Code Generation on Django

Metric: BLEU Score (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	BLEU Score▼	Extra Data	Paper	Date↕	Code
1	MarianCG	90.41	No	-	-	Code
2	LUKEMarian	89.34	No	-	-	Code
3	RoBERTaMarian	88.91	No	-	-	Code
4	TranX + BERT w/mined	79.86	No	The impact of lexical and grammatical processing...	2022-02-28	Code
5	lpn (Ling et al., 2016)	77.6	No	Latent Predictor Networks for Code Generation	2016-03-22	Code
6	BERTMarian	56.55	No	-	-	Code
7	ELECTRAMarian	53.02	No	-	-	Code
8	Phrasal Statistical MT (Ling et al., 2016)	47.6	No	Latent Predictor Networks for Code Generation	2016-03-22	Code

#1MarianCG
90.41
BLEU Score
No paperCode
#2LUKEMarian
89.34
BLEU Score
No paperCode
#3RoBERTaMarian
88.91
BLEU Score
No paperCode
#4TranX + BERT w/minedSOTA
79.86
BLEU Score· 2022-02-28
The impact of lexical and grammatical processing on generating code from natural language Code
#5lpn (Ling et al., 2016)SOTA
77.6
BLEU Score· 2016-03-22
Latent Predictor Networks for Code Generation Code
#6BERTMarian
56.55
BLEU Score
No paperCode
#7ELECTRAMarian
53.02
BLEU Score
No paperCode
#8Phrasal Statistical MT (Ling et al., 2016)
47.6
BLEU Score· 2016-03-22
Latent Predictor Networks for Code Generation Code