{"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/l0-reasoning-bench-evaluating-procedural","title":"L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution","arxiv_id":"2503.22832","date":"2025-03-28","proceeding":null,"authors":["Simeng Sun","Cheng-Ping Hsieh","Faisal Ladhak","Erik Arakelyan","Santiago Akle Serano","Boris Ginsburg"],"abstract":"Complex reasoning tasks often rely on the ability to consistently and accurately apply simple rules across incremental steps, a foundational capability which we term \"level-0\" reasoning. To systematically evaluate this capability, we introduce L0-Bench, a language model benchmark for testing procedural correctness -- the ability to generate correct reasoning processes, complementing existing benchmarks that primarily focus on outcome correctness. Given synthetic Python functions with simple operations, L0-Bench grades models on their ability to generate step-by-step, error-free execution traces. The synthetic nature of L0-Bench enables systematic and scalable generation of test programs along various axes (e.g., number of trace steps). We evaluate a diverse array of recent closed-source and open-weight models on a baseline test set. All models exhibit degradation as the number of target trace steps increases, while larger models and reasoning-enhanced models better maintain correctness over multiple steps. Additionally, we use L0-Bench to explore test-time scaling along three dimensions: input context length, number of solutions for majority voting, and inference steps. Our results suggest substantial room to improve \"level-0\" reasoning and potential directions to build more reliable reasoning systems.","url_abs":"https://arxiv.org/abs/2503.22832v2","url_pdf":"https://arxiv.org/pdf/2503.22832v2.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":"l0-reasoning-bench-evaluating-procedural","repo_url":"https://github.com/SimengSun/L0-reasoning-bench","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.22832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.22832"}},"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/SimengSun/L0-reasoning-bench","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"a792b767fa29dc73","entry":"disassemble_bytecode","repo":"SimengSun/L0-reasoning-bench","repo_kind":"official","path":"src/generators/tracer.py","file_url":"https://github.com/SimengSun/L0-reasoning-bench/blob/HEAD/src/generators/tracer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a792b767fa29dc73"}},{"code_sha256_prefix":"e8bc1626885dad26","entry":"extract_function_args","repo":"SimengSun/L0-reasoning-bench","repo_kind":"official","path":"src/generators/generator.py","file_url":"https://github.com/SimengSun/L0-reasoning-bench/blob/HEAD/src/generators/generator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8bc1626885dad26"}},{"code_sha256_prefix":"71ddff6c85c17c24","entry":"filter_trace","repo":"SimengSun/L0-reasoning-bench","repo_kind":"official","path":"src/generators/tracer.py","file_url":"https://github.com/SimengSun/L0-reasoning-bench/blob/HEAD/src/generators/tracer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71ddff6c85c17c24"}},{"code_sha256_prefix":"fcdb1a6da02ce36b","entry":"generate_trace","repo":"SimengSun/L0-reasoning-bench","repo_kind":"official","path":"src/generators/tracer.py","file_url":"https://github.com/SimengSun/L0-reasoning-bench/blob/HEAD/src/generators/tracer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fcdb1a6da02ce36b"}},{"code_sha256_prefix":"ab69c6df9a3fcc99","entry":"is_arg_used","repo":"SimengSun/L0-reasoning-bench","repo_kind":"official","path":"src/generators/generator.py","file_url":"https://github.com/SimengSun/L0-reasoning-bench/blob/HEAD/src/generators/generator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab69c6df9a3fcc99"}},{"code_sha256_prefix":"2f07660b55ff5be0","entry":"load_yaml_config","repo":"SimengSun/L0-reasoning-bench","repo_kind":"official","path":"src/evaluators/launcher.py","file_url":"https://github.com/SimengSun/L0-reasoning-bench/blob/HEAD/src/evaluators/launcher.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f07660b55ff5be0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}