{"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":"/paper/can-1b-llm-surpass-405b-llm-rethinking","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","arxiv_id":"2502.06703","date":"2025-02-10","proceeding":null,"authors":["Runze Liu","Junqi Gao","Jian Zhao","Kaiyan Zhang","Xiu Li","Biqing Qi","Wanli Ouyang","BoWen Zhou"],"abstract":"Test-Time Scaling (TTS) is an important method for improving the performance of Large Language Models (LLMs) by using additional computation during the inference phase. However, current studies do not systematically analyze how policy models, Process Reward Models (PRMs), and problem difficulty influence TTS. This lack of analysis limits the understanding and practical use of TTS methods. In this paper, we focus on two core questions: (1) What is the optimal approach to scale test-time computation across different policy models, PRMs, and problem difficulty levels? (2) To what extent can extended computation improve the performance of LLMs on complex tasks, and can smaller language models outperform larger ones through this approach? Through comprehensive experiments on MATH-500 and challenging AIME24 tasks, we have the following observations: (1) The compute-optimal TTS strategy is highly dependent on the choice of policy model, PRM, and problem difficulty. (2) With our compute-optimal TTS strategy, extremely small policy models can outperform larger models. For example, a 1B LLM can exceed a 405B LLM on MATH-500. Moreover, on both MATH-500 and AIME24, a 0.5B LLM outperforms GPT-4o, a 3B LLM surpasses a 405B LLM, and a 7B LLM beats o1 and DeepSeek-R1, while with higher inference efficiency. These findings show the significance of adapting TTS strategies to the specific characteristics of each task and model and indicate that TTS is a promising approach for enhancing the reasoning abilities of LLMs.","url_abs":"https://arxiv.org/abs/2502.06703v1","url_pdf":"https://arxiv.org/pdf/2502.06703v1.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":"can-1b-llm-surpass-405b-llm-rethinking","repo_url":"https://github.com/RyanLiu112/compute-optimal-tts","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"math","task_name":"Math"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.06703","atlas_url":"https://app.syntology.ai/?focus=2502.06703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06703"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.06703"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2502.06703"},"call":"get_harvested_code_for_paper(arxiv_id=\"2502.06703\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2502.06703"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2502.06703\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2502.06703"},"call":"get_concepts_for_paper(arxiv_id=\"2502.06703\")"}],"by_repo":[{"repo":"RyanLiu112/compute-optimal-tts","kind":"official","samples":13,"ran":9,"instrument":2,"unverified":4}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2502.06703.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2502.06703.svg"},"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/RyanLiu112/compute-optimal-tts","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_honours":2,"ran":3,"ran_violates":2,"unverified":4},"n_samples":13,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_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'","n_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)"},"by_repo_kind":{"official":{"samples":13,"ran":9,"n_ran_checked":7,"n_instrument":2,"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":4,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":4,"fixture_fields_is":{"signature_and_fixture_out_type":"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_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":9,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"809c0178a7ae90ff","code_sha256_prefix":"809c0178a7ae90ff","entry":"choice_answer_clean","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/grader.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/grader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"pred:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","retrieve_with":{"tool":"get_code","code_sha256":"809c0178a7ae90ff"},"code_page":"/code/choice-answer-clean","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from QwenLM/Qwen2.5-Math, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"809c0178a7ae90ff"}},{"code_sha256":"368d3db6347269c3","code_sha256_prefix":"368d3db6347269c3","entry":"count_unknown_letters_in_expr","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/verify_utils.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/verify_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"expr:str/0/str","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"368d3db6347269c3"},"code_page":"/code/count-unknown-letters-in-expr","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"368d3db6347269c3"}},{"code_sha256":"5e9f6ab031880280","code_sha256_prefix":"5e9f6ab031880280","entry":"get_model_name","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"model_name_or_path:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","retrieve_with":{"tool":"get_code","code_sha256":"5e9f6ab031880280"},"code_page":"/code/get-model-name","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5e9f6ab031880280"}},{"code_sha256":"105b6f113614fb89","code_sha256_prefix":"105b6f113614fb89","entry":"get_root","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/reason/guided_search/tree.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/reason/guided_search/tree.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"node:Node/0/?","fixture_out_type":"Node","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"105b6f113614fb89"}},{"code_sha256":"fb37d3c84b18e368","code_sha256_prefix":"fb37d3c84b18e368","entry":"is_digit","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/grader.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/grader.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"num:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","code_page":"/code/is-digit","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from QwenLM/Qwen2.5-Math, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"fb37d3c84b18e368"}},{"code_sha256":"6d13ee4c8c032e97","code_sha256_prefix":"6d13ee4c8c032e97","entry":"is_file_exists","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"file_path:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-24T23:25:36.931776+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6d13ee4c8c032e97"}},{"code_sha256":"101b1e54fcdadf90","code_sha256_prefix":"101b1e54fcdadf90","entry":"normalize_answer","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/verify_utils.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/verify_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"answer:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"101b1e54fcdadf90"},"code_page":"/code/normalize-answer","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from PKU-SEC-Lab/SPEX, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"101b1e54fcdadf90"}},{"code_sha256":"7d4b7f8c3875b126","code_sha256_prefix":"7d4b7f8c3875b126","entry":"parse_digits","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/grader.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/grader.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"num:str/0/str","fixture_out_type":"float","level_recorded_at":"2026-09-25T06:02:23.992132+00:00","retrieve_with":{"tool":"get_code","code_sha256":"7d4b7f8c3875b126"},"code_page":"/code/parse-digits","census":null,"licence":"MIT","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from QwenLM/Qwen2.5-Math, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"7d4b7f8c3875b126"}},{"code_sha256":"95f02454eddf082a","code_sha256_prefix":"95f02454eddf082a","entry":"should_allow_eval","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/verify_utils.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/verify_utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"expr:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/should-allow-eval","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"95f02454eddf082a"}},{"code_sha256":"042094830d54a879","code_sha256_prefix":"042094830d54a879","entry":"extract_answer","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/env.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/env.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/extract-answer","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"042094830d54a879"}},{"code_sha256":"664b4759319bf405","code_sha256_prefix":"664b4759319bf405","entry":"extract_groundtruth","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/env.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/env.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"664b4759319bf405"}},{"code_sha256":"c47dcad7c32e67e8","code_sha256_prefix":"c47dcad7c32e67e8","entry":"is_file_empty","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c47dcad7c32e67e8"}},{"code_sha256":"25655b21b478adb7","code_sha256_prefix":"25655b21b478adb7","entry":"judge_correct","repo":"RyanLiu112/compute-optimal-tts","repo_kind":"official","path":"src/envs/MATH/env.py","file_url":"https://github.com/RyanLiu112/compute-optimal-tts/blob/HEAD/src/envs/MATH/env.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"25655b21b478adb7"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ef1f5a9c0de50fd6c5bbd11200afc524339dbaf0fb11b29d7e85c38c91cad164","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}