SOTAVerified

Code Generation

Code Generation is an important field to predict explicit code or program structure from multimodal data sources such as incomplete code, programs in another programming language, natural language descriptions or execution examples. Code Generation tools can assist the development of automatic programming tools to improve programming productivity.

Source: Deep Learning for Source Code Modeling and Generation

Image source: Measuring Coding Challenge Competence With APPS

Papers

Showing 201250 of 1697 papers

TitleStatusHype
HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code GenerationCode1
Data-efficient LLM Fine-tuning for Code GenerationCode1
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code GenerationCode1
How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality DataCode1
HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding TasksCode1
CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science MasteryCode1
CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code GenerationCode1
GUI Element Detection Using SOTA YOLO Deep Learning ModelsCode1
GRILLBot In Practice: Lessons and Tradeoffs Deploying Large Language Models for Adaptable Conversational Task AssistantsCode1
Automating the Design of Multigrid Methods with Evolutionary Program SynthesisCode1
CoTexT: Multi-task Learning with Code-Text TransformerCode1
HALO: Hierarchical Autonomous Logic-Oriented Orchestration for Multi-Agent LLM SystemsCode1
HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language GeneralizationCode1
GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation ModelsCode1
Controlling Conditional Language Models without Catastrophic ForgettingCode1
Analysis of Tree-Structured Architectures for Code GenerationCode1
Large Language Models for Code: Security Hardening and Adversarial TestingCode1
GNNBuilder: An Automated Framework for Generic Graph Neural Network Accelerator Generation, Simulation, and OptimizationCode1
Automatic Generation of Python Programs Using Context-Free GrammarsCode1
Getting the most out of your tokenizer for pre-training and domain adaptationCode1
Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program RepairCode1
Automatic Unit Test Data Generation and Actor-Critic Reinforcement Learning for Code SynthesisCode1
Constrained Decoding for Secure Code GenerationCode1
Automatic Code Generation using Pre-Trained Language ModelsCode1
CYCLE: Learning to Self-Refine the Code GenerationCode1
ContraCLM: Contrastive Learning For Causal Language ModelCode1
Compositional Exemplars for In-context LearningCode1
Compliance-to-Code: Enhancing Financial Compliance Checking via Code GenerationCode1
AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic PapersCode1
Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code ContributionsCode1
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree SearchCode1
AutoSafeCoder: A Multi-Agent Framework for Securing LLM Code Generation through Static Analysis and Fuzz TestingCode1
Gemini: A Family of Highly Capable Multimodal ModelsCode1
Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive PrinciplesCode1
Generating Data for Symbolic Language with Large Language ModelsCode1
FullFront: Benchmarking MLLMs Across the Full Front-End Engineering WorkflowCode1
CoreCodeBench: A Configurable Multi-Scenario Repository-Level BenchmarkCode1
FVEval: Understanding Language Model Capabilities in Formal Verification of Digital HardwareCode1
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and InteractivityCode1
Code-Vision: Evaluating Multimodal LLMs Logic Understanding and Code Generation CapabilitiesCode1
CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance ComputingCode1
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and GenerationCode1
AutoDroid-V2: Boosting SLM-based GUI Agents via Code GenerationCode1
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language ModelsCode1
AutoDiCE: Fully Automated Distributed CNN Inference at the EdgeCode1
Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric ApproachCode1
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and GenerationCode1
From Things' Modeling Language (ThingML) to Things' Machine Learning (ThingML2)Code1
Benchmarking Language Model Creativity: A Case Study on Code GenerationCode1
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and GenerationCode1
Show:102550
← PrevPage 5 of 34Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EG-CFG (DeepSeek-V3-0324)Accuracy96.6Unverified
2QualityFlow (Sonnet-3.5)Accuracy94.2Unverified
3o1-mini + MapCoder (Hamming.ai)Accuracy93.2Unverified
4MGDebugger (DeepSeek-V3-0324)Accuracy92.4Unverified
5GPT-4 + AgentCoderAccuracy91.8Unverified
6CodeSim (GPT4o)Accuracy90.7Unverified
7Jiutian-大模型Accuracy90Unverified
8GPT-3.5 Turbo (ChatGPT) + AgentCoderAccuracy89.9Unverified
9MapCoder (GPT-4o)Accuracy89.7Unverified
10GPT-4 (ChatGPT Plus)Accuracy87.5Unverified
#ModelMetricClaimedVerifiedStatus
1LPW (GPT-4o)Introductory Pass@187.2Unverified
2MoTCoder-32B-V1.5Introductory Pass@168.44Unverified
3MoTCoder-7B-V1.5Introductory Pass@154.26Unverified
4code-davinci-002 175B (CodeT)Introductory Pass@147.3Unverified
5deepseek-ai/deepseek-coder-6.7b-instructIntroductory Pass@133.8Unverified
6code-davinci-002 175BIntroductory Pass@131.92Unverified
7CodeChain+WizardCoder-15bIntroductory Pass@129.3Unverified
8WizardCoder-15bIntroductory Pass@126.29Unverified
9CodeSim (GPT4)Introductory Pass@126.04Unverified
10AlphaCode 1B Filtered from 50000Competition Pass@any22Unverified
#ModelMetricClaimedVerifiedStatus
1PanGu-Coder-FT-IBLEU44.32Unverified
2RoBERTaMarianBLEU35.74Unverified
3MarianCGBLEU34.43Unverified
4TranX + BERT w/minedBLEU34.2Unverified
5BERT + TAEBLEU33.41Unverified
6BERTMarianBLEU32.46Unverified
7External Knowledge With API + RerankingBLEU32.26Unverified
8External Knowledge With APIBLEU30.69Unverified
9BART W/ MinedBLEU30.55Unverified
10ELECTRAMarianBLEU30.18Unverified
#ModelMetricClaimedVerifiedStatus
1MarianCGAccuracy81.83Unverified
2BERT + TAEAccuracy81.03Unverified
3TranX + BERT w/minedAccuracy81.03Unverified
4RerankerAccuracy80.2Unverified
5LUKEMarianAccuracy78.5Unverified
6RoBERTaMarianAccuracy77.95Unverified
7BERTMarianAccuracy76.68Unverified
8TranxAccuracy73.7Unverified
9ELECTRAMarianAccuracy65.32Unverified
10lpn (Ling et al., 2016)Accuracy62.3Unverified
#ModelMetricClaimedVerifiedStatus
1NL2SQL-RULEExecution Accuracy89.2Unverified
2TypeSQL+TC (Yu et al., 2018)+Execution Accuracy82.6Unverified
3TranxExecution Accuracy78.6Unverified
4STAMP+RL (Sun et al., 2018)+Execution Accuracy74.6Unverified
5STAMP (Sun et al., 2018)+Execution Accuracy74.4Unverified
6TypeSQL (Yu et al., 2018)Execution Accuracy73.5Unverified
7PT-MAML (Huang et al., 2018)Execution Accuracy68Unverified
8Bidirectional Attention for SQL GenerationExecution Accuracy62.5Unverified
9Seq2SQL (Zhong et al., 2017)Execution Accuracy59.4Unverified
10Seq2Seq (Zhong et al., 2017)Execution Accuracy35.9Unverified
#ModelMetricClaimedVerifiedStatus
1QurrentOS-coder + Claude 3.5 Sonnetpass@158Unverified
2QurrentOS-coder + GPT-4opass@146Unverified
3QurrentOS-coder + GPT-4 Turbopass@137Unverified
4QurrentOS-coder + Claude 3 Opuspass@136Unverified
5QurrentOS-coder + Gemini 1.5 Propass@130Unverified
6QurrentOS-coder + GPT-4pass@130Unverified
7QurrentOS-coder + DeepSeek-Coder-V2pass@129Unverified
8QurrentOS-coder + Llama 3 70bpass@120Unverified
9QurrentOS-coder + Qwen-72B-Instructpass@118Unverified
#ModelMetricClaimedVerifiedStatus
1EG-CFG (DeepSeek-V3-0324)Test Set pass@158.18Unverified
2LPW (GPT-4o)Test Set pass@134.7Unverified
3MapCoder (GPT-4)Test Set pass@128.5Unverified
4CodeSim (GPT4)Test Set pass@128.4Unverified
5MoTCoder-15BTest Set pass@126.34Unverified
6MoTCoder-7B-v1.5Test Set pass@120.77Unverified
7CodeChain + WizardCoder-15BTest Set pass@12.35Unverified
8WizardCoder-15BTest Set pass@11.11Unverified
#ModelMetricClaimedVerifiedStatus
1DeepSeek-R1 (MGDebugger)Pass@1100Unverified
2LLaMA 3Pass@199.4Unverified
3QualityFlow (Sonnet-3.5)Pass@198.8Unverified
4Phi-2Pass@198.2Unverified
5EG-CFG (DeepSeek-V3-0324)Pass@196.95Unverified
6Mistral 7BPass@193.9Unverified
7Claude Sonnet 3.5Pass@190.85Unverified
8L2MAC (GPT-4)Pass@190.2Unverified
#ModelMetricClaimedVerifiedStatus
1Claude 3 HaikuPass@327.67Unverified
2GPT-3.5 TurboPass@323.75Unverified
3codechat-bisonPass@311.39Unverified
4chat-bisonPass@38.48Unverified
5Mixtral-8x7B-InstructPass@38.35Unverified
6Phi-3-mini-128k-instructPass@37.18Unverified
7WizardLM-2-7BPass@33.72Unverified
8Llama-3-8B-InstructPass@33.1Unverified
#ModelMetricClaimedVerifiedStatus
1o1-previewpass@10.95Unverified
2o1-minipass@10.94Unverified
3gpt-4o-2024-08-06pass@10.89Unverified
4claude-3.5-sonnetpass@10.88Unverified
5deepseek-v2.5pass@10.83Unverified
6mistral-large-2pass@10.78Unverified
7deepseek-coder-v2-instructpass@10.7Unverified
8llama-v3p1-405b-instructpass@10.3Unverified
#ModelMetricClaimedVerifiedStatus
1BART W/ MinedBLEU35.32Unverified
2BART BaseBLEU34.35Unverified
3External Knowledge With API + RerankingBLEU20.54Unverified
4External Knowledge With APIBLEU20.37Unverified
5RerankerBLEU19.85Unverified
6TranXBLEU18.85Unverified
#ModelMetricClaimedVerifiedStatus
1claude-3-5-sonnetpass@10.68Unverified
2o1-minipass@10.67Unverified