{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/s3eval-a-synthetic-scalable-systematic","title":"S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models","arxiv_id":"2310.15147","date":"2023-10-23","proceeding":null,"authors":["Fangyu Lei","Qian Liu","Yiming Huang","Shizhu He","Jun Zhao","Kang Liu"],"abstract":"The rapid development of Large Language Models (LLMs) has led to great strides in model capabilities like long-context understanding and reasoning. However, as LLMs are able to process longer contexts, it becomes more challenging to evaluate whether they have acquired certain capabilities, since the length of text (e.g., 200K tokens) they can process far exceeds what humans can reliably assess in a reasonable duration. In this paper, we propose using complex synthetic tasks as a proxy evaluation method, and present S3Eval, a Synthetic, Scalable, Systematic evaluation suite for LLMs evaluation. The synthetic nature of S3Eval provides users full control over the dataset, allowing them to systematically probe LLM capabilities by scaling text length and varying task difficulty across diverse scenarios. The strong correlation between S3Eval and real-world benchmarks demonstrates the soundness of using S3Eval for evaluation of LLMs. S3Eval provides a flexible and infinite long-context data generation method. We have generated a comprehensive dataset called S3Eval-Standard, and experimental results have shown that it poses significant challenges for all existing LLMs.","url_abs":"https://arxiv.org/abs/2310.15147v2","url_pdf":"https://arxiv.org/pdf/2310.15147v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"s3eval-a-synthetic-scalable-systematic","repo_url":"https://github.com/lfy79001/s3eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"s3eval-a-synthetic-scalable-systematic","repo_url":"https://github.com/lfy79001/sqleval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"long-context-understanding","task_name":"Long-Context Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.15147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15147"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lfy79001/sqleval","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lfy79001/s3eval","reach":{"status":"ok"}}],"summary":{"ran":21,"unverified":5},"by_repo_kind":{"official":{"samples":26,"ran":21,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":26,"samples":[{"code_sha256_prefix":"3c0b91f1646bac21","entry":"control_sql_general","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/coarse_template.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/coarse_template.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c0b91f1646bac21"}},{"code_sha256_prefix":"5719e3e694b76e1e","entry":"control_sql_general","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/coarse_template_real.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/coarse_template_real.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5719e3e694b76e1e"}},{"code_sha256_prefix":"5a422eaf7dbfe626","entry":"control_sql_general","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/coarse_template_zh.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/coarse_template_zh.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a422eaf7dbfe626"}},{"code_sha256_prefix":"447f107d4d5afc3a","entry":"convert_to_number","repo":"lfy79001/s3eval","repo_kind":"official","path":"eval/claude.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/eval/claude.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"447f107d4d5afc3a"}},{"code_sha256_prefix":"cd59b0e07b4a9092","entry":"find_element_position","repo":"lfy79001/s3eval","repo_kind":"official","path":"eval/claude.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/eval/claude.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd59b0e07b4a9092"}},{"code_sha256_prefix":"f8a9f700d9dc2244","entry":"find_position","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/fine_template_utils.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/fine_template_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8a9f700d9dc2244"}},{"code_sha256_prefix":"78df3466953b44fb","entry":"generate_multiturn","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/fine_template_utils.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/fine_template_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"78df3466953b44fb"}},{"code_sha256_prefix":"a8c20dc77d641620","entry":"generate_multiturn_zh","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/fine_template_utils.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/fine_template_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a8c20dc77d641620"}},{"code_sha256_prefix":"584fb6e3716802c1","entry":"generate_prompt_format","repo":"lfy79001/sqleval","repo_kind":"official","path":"eval/llama2.py","file_url":"https://github.com/lfy79001/sqleval/blob/HEAD/eval/llama2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"584fb6e3716802c1"}},{"code_sha256_prefix":"b9e6eedf2bc665a0","entry":"generate_random_date_of_birth","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/value_utils.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/value_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b9e6eedf2bc665a0"}},{"code_sha256_prefix":"3ef77f8cc6bf2eb3","entry":"generate_random_number","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/coarse_template.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/coarse_template.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3ef77f8cc6bf2eb3"}},{"code_sha256_prefix":"e272418892cb953e","entry":"get_column_type","repo":"lfy79001/s3eval","repo_kind":"official","path":"convert_csv.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/convert_csv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e272418892cb953e"}},{"code_sha256_prefix":"18dbbf0eed3bcc2f","entry":"get_file_paths","repo":"lfy79001/s3eval","repo_kind":"official","path":"convert_csv.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/convert_csv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"18dbbf0eed3bcc2f"}},{"code_sha256_prefix":"d592622e23006758","entry":"get_table_length","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/table_utils.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/table_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d592622e23006758"}},{"code_sha256_prefix":"96d8dd4ea02817fe","entry":"has_duplicates","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/value_utils.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/value_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"96d8dd4ea02817fe"}},{"code_sha256_prefix":"3aedfdb61c1e5456","entry":"is_integer","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/coarse_template.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/coarse_template.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3aedfdb61c1e5456"}},{"code_sha256_prefix":"2ca80fb7cf12de69","entry":"is_numeric","repo":"lfy79001/s3eval","repo_kind":"official","path":"eval/claude.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/eval/claude.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2ca80fb7cf12de69"}},{"code_sha256_prefix":"5ee9501ae032577a","entry":"num_tokens_from_string","repo":"lfy79001/sqleval","repo_kind":"official","path":"eval/llama2.py","file_url":"https://github.com/lfy79001/sqleval/blob/HEAD/eval/llama2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ee9501ae032577a"}},{"code_sha256_prefix":"d7476bf46767ec98","entry":"random_strings","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/value_utils.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/value_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7476bf46767ec98"}},{"code_sha256_prefix":"336256046b197a5f","entry":"read_table","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/table_utils.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/table_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"336256046b197a5f"}},{"code_sha256_prefix":"0d0a77750dd4ac8d","entry":"replace_nth_occurrence","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/fine_template.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/fine_template.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0d0a77750dd4ac8d"}},{"code_sha256_prefix":"1b10075146a0cca4","entry":"control_sql","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/fine_template.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/fine_template.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b10075146a0cca4"}},{"code_sha256_prefix":"d4aca894e559c443","entry":"select_condition","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/coarse_template_real.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/coarse_template_real.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4aca894e559c443"}},{"code_sha256_prefix":"b9d41533d02bf974","entry":"select_condition","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/coarse_template_zh.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/coarse_template_zh.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b9d41533d02bf974"}},{"code_sha256_prefix":"f8da43961770d90e","entry":"template_queries","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/fine_template.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/fine_template.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f8da43961770d90e"}},{"code_sha256_prefix":"2069b559fa87d0ae","entry":"where_condition","repo":"lfy79001/s3eval","repo_kind":"official","path":"s3eval/coarse_template_zh.py","file_url":"https://github.com/lfy79001/s3eval/blob/HEAD/s3eval/coarse_template_zh.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2069b559fa87d0ae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}