Browse State-of-the-Art › Code Generation

Code Generation

745 papers with code · 27 benchmarks · 70 datasets archive 2025-07-28

Computer CodeNatural Language ProcessingReasoning

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

Description from the archive archive 2025-07-28; Papers-with-Code links inside it are rewritten to this site.

Benchmarks archive 2025-07-28

27 leaderboard tables shown for this task, 27 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 27 until expanded.

Syntology 109 newer papers were judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 6 placed): MBPP (57 judged, 4 placed), APPS (1 judged, 0 placed), HumanEval (54 judged, 0 placed), Livecodebench (16 judged, 2 placed), BigCodeBench-Instruct (2 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
MBPP (99 rows) EG-CFG (DeepSeek-V3-0324) Execution Guided Line-by-Line Code Generation code — Compare
APPS (18 rows) LPW (GPT-4o) Planning-Driven Programming: A Large Language Model Programming Workflow code Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified Compare
CoNaLa (14 rows) PanGu-Coder-FT-I Fine-Tuning Large Language Models for Answering Programming... — — Compare
Django (11 rows) MarianCG MarianCG: a code generation transformer model inspired by machine... code — Compare
WikiSQL (10 rows) NL2SQL-RULE Content Enhanced BERT-based Text-to-SQL Generation code — Compare
RES-Q (9 rows) QurrentOS-coder + Claude 3.5 Sonnet RES-Q: Evaluating Code-Editing Large Language Model Systems at the... code Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified Compare
CodeContests (8 rows) EG-CFG (DeepSeek-V3-0324) Execution Guided Line-by-Line Code Generation code — Compare
HumanEval (8 rows) DeepSeek-R1 (MGDebugger) From Code to Correctness: Closing the Last Mile of Code Generation... code Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified Compare
PECC (8 rows) Claude 3 Haiku PECC: Problem Extraction and Coding Challenges code — Compare
WebApp1K-React (8 rows) o1-preview A Case Study of Web App Coding with OpenAI Reasoning Models code — Compare
CoNaLa-Ext (6 rows) BART W/ Mined Reading StackOverflow Encourages Cheating: Adding Question Text... code — Compare
WebApp1k-Duo-React (6 rows) claude-3-5-sonnet A Case Study of Web App Coding with OpenAI Reasoning Models code — Compare
DSEval-LeetCode (5 rows) Jupyter-AI — — — Compare
Turbulence (5 rows) GPT-4 Turbulence: Systematically and Automatically Testing... code Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
Livecodebench (3 rows) Xolver Xolver: Multi-Agent Reasoning with Holistic Experience Learning... code — Compare
Shellcode_IA32 (3 rows) CodeBERT Can We Generate Shellcodes via Natural Language? An Empirical Study code — Compare
TACO-BAAI (3 rows) GPT-4 TACO: Topics in Algorithmic COde generation dataset code Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
BigCodeBench-Complete (2 rows) GPT-4o-2024-05-13 BigCodeBench: Benchmarking Code Generation with Diverse Function... code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified Compare
BigCodeBench-Instruct (2 rows) GPT-4o-2024-05-13 BigCodeBench: Benchmarking Code Generation with Diverse Function... code Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified Compare
CodeXGLUE - CodeSearchNet (2 rows) Redcoder-ext Retrieval Augmented Code Generation and Summarization code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
CONCODE (2 rows) Redcoder-ext Retrieval Augmented Code Generation and Summarization code Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified Compare
HumanEval-ET (2 rows) EG-CFG (DeepSeek-V3-0324) Execution Guided Line-by-Line Code Generation code — Compare
MBPP-ET (2 rows) EG-CFG (DeepSeek-V3-0324) Execution Guided Line-by-Line Code Generation code — Compare
Verified Smart Contract Code Comments (2 rows) GPT-J 6B Smart Contract Efficient Avoidance of Vulnerabilities in Auto-completed Smart... — — Compare
Android Repos (1 row) Entity Type Model Building Language Models for Text with Named Entities code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
FloCo (1 row) FloCo-T5 Towards Making Flowchart Images Machine Interpretable code — Compare
VerilogEval (1 row) Nexus (Claude 3.5 Sonnet) Nexus: A Lightweight and Scalable Multi-Agent Framework for... code — Compare

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

70 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 70 until expanded.

Subtasks archive 2025-07-28

5 subtasks in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 1,697 · with a code link: 745 · where Syntology ran a sample: 280 (224 with a run with no instrument failure, 56 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (280 of 1,697 tagged: 224 with a run with no instrument failure, 56 where every run was a failure of Syntology's instrument)

Page 1 of 17: papers 1 to 100 of 1,697, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

Syntology lines on 62 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections