{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/cybench","name":"Cybench","full_name":null,"description_markdown":"Language Model (LM) agents for cybersecurity that are capable of autonomously identifying vulnerabilities and executing exploits have potential to cause real-world impact. Policymakers, model providers, and researchers in the AI and cybersecurity communities are interested in quantifying the capabilities of such agents to help mitigate cyberrisk and investigate opportunities for penetration testing. Toward that end, we introduce Cybench, a framework for specifying cybersecurity tasks and evaluating agents on those tasks. We include 40 professional-level Capture the Flag (CTF) tasks from 4 distinct CTF competitions, chosen to be recent, meaningful, and spanning a wide range of difficulties. Each task includes its own description, starter files, and is initialized in an environment where an agent can execute commands and observe outputs. Since many tasks are beyond the capabilities of existing LM agents, we introduce subtasks for each task, which break down a task into intermediary steps for a more detailed evaluation. To evaluate agent capabilities, we construct a cybersecurity agent and evaluate 8 models: GPT-4o, OpenAI o1-preview, Claude 3 Opus, Claude 3.5 Sonnet, Mixtral 8x22b Instruct, Gemini 1.5 Pro, Llama 3 70B Chat, and Llama 3.1 405B Instruct. For the top performing models (GPT-4o and Claude 3.5 Sonnet), we further investigate performance across 4 agent scaffolds (structed bash, action-only, pseudoterminal, and web search). Without subtask guidance, agents leveraging Claude 3.5 Sonnet, GPT-4o, OpenAI o1-preview, and Claude 3 Opus successfully solved complete tasks that took human teams up to 11 minutes to solve. In comparison, the most difficult task took human teams 24 hours and 54 minutes to solve. All code and data are publicly available at https://cybench.github.io/.","description_withheld":null,"homepage":"https://cybench.github.io/","introduced_date":"2024-08-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/cybench-a-framework-for-evaluating","title":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models","first_author":"Andy K. Zhang","url":null},"license":null,"modalities":[],"tasks":[{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"}],"languages":[],"variants":["Cybench"],"data_loaders":[],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/on-cybench","task":"","dataset_variant":"Cybench","rows":3,"metrics":["Unguided Performance"],"first_row_in_archive_order":{"model":"Claude 3.5 Sonnet (old, US AISI scaffold, pass@10)","paper":"/paper/us-aisi-and-uk-aisi-joint-pre-deployment-test-1","metrics":{"Unguided Performance":"35%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":2,"of":2,"counts":{"papers_with_a_benchmark_row":2,"with_a_code_link":1,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":2,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/us-aisi-and-uk-aisi-joint-pre-deployment-test-1","slug":"us-aisi-and-uk-aisi-joint-pre-deployment-test-1","title":"US AISI and UK AISI Joint Pre-Deployment Test: Anthropic’s Claude 3.5 Sonnet (October 2024 Release)","date":"2024-11-19","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/cybench-a-framework-for-evaluating","slug":"cybench-a-framework-for-evaluating","title":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models","date":"2024-08-15","arxiv_id":"2408.08926","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["andyzorigin/cybench","andyzorigin/cyber-bench"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cybench-a-framework-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2408.08926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08926"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/us-aisi-and-uk-aisi-joint-pre-deployment-test-1","slug":"us-aisi-and-uk-aisi-joint-pre-deployment-test-1","title":"US AISI and UK AISI Joint Pre-Deployment Test: Anthropic’s Claude 3.5 Sonnet (October 2024 Release)","date":"2024-11-19","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/cybench-a-framework-for-evaluating","slug":"cybench-a-framework-for-evaluating","title":"Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risks of Language Models","date":"2024-08-15","arxiv_id":"2408.08926","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["andyzorigin/cybench","andyzorigin/cyber-bench"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cybench-a-framework-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2408.08926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08926"}}}}],"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/dataset/cybench/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/cybench/papers/ran/1","json":"/dataset/cybench/papers/ran/1.json","rows":1}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":1,"samples_harvested":10,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":5,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":1,"papers_with_a_run_with_no_instrument_failure":1,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"d594c50992379672cf9eca480b16365a3b808485d37faed13c5f418ce38acbfc","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}