Codesota · Models · CoTexTCase Western Reserve University1 results · 1 benchmarks

Model card

CoTexT.

Case Western Reserve Universitycode-lmTransformer encoder-decoder

Multi-task learning with Code-Text Transformer. Pre-trained on NL+PL data. From arXiv 2105.08645.

§ 01 · Benchmarks

Every benchmark CoTexT has a recorded score for.

#	Benchmark	Area · Task	Metric	Value	Rank	Date	Source
01	codesearchnet---java	Computer Vision · Optical Character Recognition	smoothed-bleu-4	19.1%	#6/14	—	source ↗

Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.

§ 02 · Strengths by area

Where CoTexT actually performs.

Computer Vision

benchmark

avg rank #6.0

§ 05 · Sources & freshness

Where these numbers come from.

codexglue-leaderboard

result

1 of 1 rows marked verified.