Papers › Measuring Coding Challenge Competence With APPS

Measuring Coding Challenge Competence With APPS

20 May 2021arXiv:2105.09938archive 2025-07-28

Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob Steinhardt

While programming is one of the most broadly applicable skills in modern society, modern machine learning models still cannot code solutions to basic problems. Despite its importance, there has been surprisingly little work on evaluating code generation, and it can be difficult to accurately assess code generation performance rigorously. To meet this challenge, we introduce APPS, a benchmark for code generation. Unlike prior work in more restricted settings, our benchmark measures the ability of models to take an arbitrary natural language specification and generate satisfactory Python code. Similar to how companies assess candidate software developers, we then evaluate models by checking their generated code on test cases. Our benchmark includes 10,000 problems, which range from having simple one-line solutions to being substantial algorithmic challenges. We fine-tune large language models on both GitHub and our training set, and we find that the prevalence of syntax errors is decreasing exponentially as models improve. Recent models such as GPT-Neo can pass approximately 20% of the test cases of introductory problems, so we find that machine learning models are now beginning to learn how to code. As the social significance of automatic code generation increases over the coming years, our benchmark can provide an important measure for tracking advancements.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 7 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; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 7 ran (5 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-27 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hendrycks/apps officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 7 ran (2 instrument-failed) · 4 unverified report
codedotal/gpt-code-clippy mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Evaluating Large Language Models Trained on Code (arXiv:2107.03374; that paper's own run record: 26 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 0 violated, 21 with no contract checked; 4 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
ncoop57/gpt-code-clippy mentioned on GitHubjaxApache-2.0Syntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 7 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; 2 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
5ran
4unverified

Licence: 2 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hendrycks/apps. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

hendrycks/apps official repository 11 samples, 7 ran (2 instrument-failed) · 4 unverified
create_split in 6 papers train/apps_create_split.py ran MIT (permissive) · 72342b1d3d9f4231 · report fixture: returned list · level recorded 2026-09-27
find_indentation eval/reindent.py ran MIT (permissive) here; the stored copy is pointer only · f05983c38acfa250 · report fixture: signature line:str/0/str, config:dict/0/? · returned tuple · level recorded 2026-09-24
get_question in 12 papers eval/testing_util.py ran MIT (permissive) · ed8331339b4de97c · report fixture: signature problem_list:list/1/str, prob_index:int/0/int · returned str · level recorded 2026-09-26
get_solutions in 6 papers eval/testing_util.py ran MIT (permissive) · 0c83bb0f43b8dc57 · report fixture: signature problem_list:list/1/str, prob_index:int/0/int · returned dict · level recorded 2026-09-26
get_valid_problems in 5 papers eval/testing_util.py ran · our draft was wrong MIT (permissive) · 8bbb265e59e23293 · report fixture: signature data_dir:str/0/str · returned list · level recorded 2026-09-26
replace_inline_tabs eval/reindent.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 27f23c533d62061a · report fixture: signature content:str/0/str, config:dict/0/? · returned str · level recorded 2026-09-24
rewrite_logs train/CustomTensorboardCallback.py ran MIT (permissive) · de2e007d84fab02c · report fixture: signature d:dict/0/? · returned dict · level recorded 2026-09-25
batch_bart_task train/dataset_lm/util.py unverified MIT (permissive) · 7f74025d94c22cd6 · report
batch_gpt_task train/dataset_lm/util.py unverified MIT (permissive) · 991b30911bfd77a2 · report
dummy_gpt_task train/dataset_lm/util.py unverified MIT (permissive) · 6b434bae76a3379f · report
sample_gpt_task train/dataset_apps/APPSBaseDataset.py unverified MIT (permissive) · 9c56401b1df9832c · report

Tasks

BIG-bench Machine LearningCode Generation

Datasets

Introduced by this paper, per the archive.

APPS

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation APPS GPT-Neo 2.7B Competition Pass@1 0.00% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Competition Pass@1000 11.40% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Competition Pass@5 0.00% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Competition Pass@any 11.40% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Interview Pass@1 0.57% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Interview Pass@1000 9.83% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Interview Pass@5 0.80% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Interview Pass@any 9.83% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Introductory Pass@1 3.90% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Introductory Pass@1000 27.90% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Introductory Pass@5 5.50% #14 of 18 Archive leaderboard report
Code Generation APPS GPT-Neo 2.7B Introductory Pass@any 27.90% #14 of 18 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

GPT-Neo

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