SOTAVerified|Agents Browse Leaderboard About Blog

Code Search

The goal of Code Search is to retrieve code fragments from a large code corpus that most closely match a developer’s intent, which is expressed in natural language.

Source: When Deep Learning Met Code Search

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–60 of 125 papers

Title	Date	Tasks	Status	Hype
CodeT5+: Open Code Large Language Models for Code Understanding and Generation	May 13, 2023	Arithmetic ReasoningCode Completion	CodeCode Available	0
The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation	May 9, 2023	Code GenerationCode Search	CodeCode Available	1
Code Execution with Pre-trained Language Models	May 8, 2023	Code GenerationCode Search	—Unverified	0
REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search Models	May 5, 2023	Code SearchContrastive Learning	CodeCode Available	0
Neuro-symbolic Zero-Shot Code Cloning with Cross-Language Intermediate Representation	Apr 26, 2023	C++ codeCode Search	—Unverified	0
One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization	Mar 28, 2023	AllCode Search	CodeCode Available	1
Unveiling Code Pre-Trained Models: Investigating Syntax and Semantics Capacities	Dec 20, 2022	Code CompletionCode Search	—Unverified	0
You Don't Know Search: Helping Users Find Code by Automatically Evaluating Alternative Queries	Dec 7, 2022	Code Search	—Unverified	0
Global Contrastive Batch Sampling via Optimization on Sample Permutations	Oct 23, 2022	Code SearchContrastive Learning	CodeCode Available	0
Exploring Representation-Level Augmentation for Code Search	Oct 21, 2022	Code SearchContrastive Learning	CodeCode Available	1

Show:10 25 50

← PrevPage 6 of 13Next →

All datasets CodeSearchNet CoDesc CodeXGLUE - AdvTest CodeSearchNet - Ruby CodeXGLUE - WebQueryTest CoIR

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	cpt-code M	Overall	93.5	—	Unverified
2	cpt-code S	Overall	93.4	—	Unverified
3	CodeT5+ 770M	Overall	77.4	—	Unverified
4	GraphCodeBERT	Overall	77.4	—	Unverified
5	CodeT5+ 220M	Overall	77.1	—	Unverified
6	CodeBERT	Overall	76	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Self-attention	Test MRR	0.84	—	Unverified
2	NBOW	Test MRR	0.81	—	Unverified
3	RNN	Test MRR	0.77	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CodeT5+ 770M	MRR	44.7	—	Unverified
2	CodeT5+ 220M	MRR	43.3	—	Unverified
3	CodeBERT	MRR	27.19	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Uni-SBT	MRR	0.36	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CodeBERT	Accuracy	47.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Voyage-code-002	nDCG@10	56.26	—	Unverified