{"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/tinybenchmarks-evaluating-llms-with-fewer","title":"tinyBenchmarks: evaluating LLMs with fewer examples","arxiv_id":"2402.14992","date":"2024-02-22","proceeding":null,"authors":["Felipe Maia Polo","Lucas Weber","Leshem Choshen","Yuekai Sun","Gongjun Xu","Mikhail Yurochkin"],"abstract":"The versatility of large language models (LLMs) led to the creation of diverse benchmarks that thoroughly test a variety of language models' abilities. These benchmarks consist of tens of thousands of examples making evaluation of LLMs very expensive. In this paper, we investigate strategies to reduce the number of evaluations needed to assess the performance of an LLM on several key benchmarks. For example, we show that to accurately estimate the performance of an LLM on MMLU, a popular multiple-choice QA benchmark consisting of 14K examples, it is sufficient to evaluate this LLM on 100 curated examples. We release evaluation tools and tiny versions of popular benchmarks: Open LLM Leaderboard, MMLU, HELM, and AlpacaEval 2.0. Our empirical analysis demonstrates that these tools and tiny benchmarks are sufficient to reliably and efficiently reproduce the original evaluation results.","url_abs":"https://arxiv.org/abs/2402.14992v2","url_pdf":"https://arxiv.org/pdf/2402.14992v2.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":"tinybenchmarks-evaluating-llms-with-fewer","repo_url":"https://github.com/felipemaiapolo/efficbench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"tinybenchmarks-evaluating-llms-with-fewer","repo_url":"https://github.com/felipemaiapolo/tinybenchmarks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tinybenchmarks-evaluating-llms-with-fewer","repo_url":"https://github.com/mariushobbhahn/swebench-verified-mini","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tinybenchmarks-evaluating-llms-with-fewer","repo_url":"https://github.com/sentient-agi/oml-1.0-fingerprinting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"mmlu","task_name":"MMLU"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.14992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14992"}},"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/felipemaiapolo/tinybenchmarks","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/felipemaiapolo/efficbench","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mariushobbhahn/swebench-verified-mini","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sentient-agi/oml-1.0-fingerprinting","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":9,"ran_violates":1,"unverified":29},"by_repo_kind":{"official":{"samples":22,"ran":10,"repositories":2},"listed":{"samples":17,"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":17,"samples":[{"code_sha256_prefix":"f79b7ee882bf1224","entry":"get_data","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"run_experiment.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/run_experiment.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":"f79b7ee882bf1224"}},{"code_sha256_prefix":"3f37f4d4e8b9e152","entry":"get_datas","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"generating_data/download-openllmleaderboard/download_model_names/openllm.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/generating_data/download-openllmleaderboard/download_model_names/openllm.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":"3f37f4d4e8b9e152"}},{"code_sha256_prefix":"c030bb619c641f8c","entry":"get_lambda","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"utils.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/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":"c030bb619c641f8c"}},{"code_sha256_prefix":"d173066d5ff1fb67","entry":"item_curve","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"utils.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/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":"d173066d5ff1fb67"}},{"code_sha256_prefix":"921caf5fc3c2b540","entry":"item_curve","repo":"felipemaiapolo/tinybenchmarks","repo_kind":"official","path":"demo/utils.py","file_url":"https://github.com/felipemaiapolo/tinybenchmarks/blob/HEAD/demo/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"921caf5fc3c2b540"}},{"code_sha256_prefix":"a744fa187a860f72","entry":"load_irt_parameters","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"irt.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/irt.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":"a744fa187a860f72"}},{"code_sha256_prefix":"ef3515d9063526b8","entry":"prepare_data","repo":"felipemaiapolo/tinybenchmarks","repo_kind":"official","path":"tutorials/utils.py","file_url":"https://github.com/felipemaiapolo/tinybenchmarks/blob/HEAD/tutorials/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef3515d9063526b8"}},{"code_sha256_prefix":"a911f9cacbc9faf4","entry":"sigmoid","repo":"felipemaiapolo/tinybenchmarks","repo_kind":"official","path":"demo/utils.py","file_url":"https://github.com/felipemaiapolo/tinybenchmarks/blob/HEAD/demo/utils.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a911f9cacbc9faf4"}},{"code_sha256_prefix":"613d5fa522ce2fe7","entry":"sigmoid","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"utils.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/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":"613d5fa522ce2fe7"}},{"code_sha256_prefix":"f9a2099f222c55c0","entry":"winrate","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"plots.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/plots.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":"f9a2099f222c55c0"}},{"code_sha256_prefix":"665d15ac51c28fd5","entry":"calculate_accuracies","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"acc.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/acc.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":"665d15ac51c28fd5"}},{"code_sha256_prefix":"3e37b7d40582ad9d","entry":"check_file_exists","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"run_all.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/run_all.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e37b7d40582ad9d"}},{"code_sha256_prefix":"bf1d584f11529d41","entry":"compare_difficulty_distributions","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"compare_subsets.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/compare_subsets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf1d584f11529d41"}},{"code_sha256_prefix":"fd966a7ef33f7a71","entry":"compare_means","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"compare_subsets.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/compare_subsets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd966a7ef33f7a71"}},{"code_sha256_prefix":"db63652efa566108","entry":"compute_acc_pirt","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"acc.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/acc.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":"db63652efa566108"}},{"code_sha256_prefix":"44ffb79d93d3714c","entry":"compute_kmeans","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"generate_subsets.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/generate_subsets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44ffb79d93d3714c"}},{"code_sha256_prefix":"607e7cb82032195e","entry":"convert_to_gb","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"get_docker_image_sizes.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/get_docker_image_sizes.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"607e7cb82032195e"}},{"code_sha256_prefix":"8ae80ca052410f1d","entry":"count_test_results","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"extract_data_from_logs.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/extract_data_from_logs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ae80ca052410f1d"}},{"code_sha256_prefix":"ac93c19afba2b273","entry":"draw_representative_sample","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"generate_subsets.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/generate_subsets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac93c19afba2b273"}},{"code_sha256_prefix":"a0e44adf60096817","entry":"estimate_ability_parameters","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"irt.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/irt.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":"a0e44adf60096817"}},{"code_sha256_prefix":"5cfb956fb08b8f0e","entry":"estimate_ability_parameters","repo":"felipemaiapolo/tinybenchmarks","repo_kind":"official","path":"tutorials/irt.py","file_url":"https://github.com/felipemaiapolo/tinybenchmarks/blob/HEAD/tutorials/irt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cfb956fb08b8f0e"}},{"code_sha256_prefix":"1153f14380c21738","entry":"evaluate_scenarios","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"experiments.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/experiments.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":"1153f14380c21738"}},{"code_sha256_prefix":"bac16ddf5e843b55","entry":"filter_dataset_by_ids","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"make_new_huggingface_dataset.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/make_new_huggingface_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bac16ddf5e843b55"}},{"code_sha256_prefix":"bfcec22b9dae71a3","entry":"fit_theta","repo":"felipemaiapolo/tinybenchmarks","repo_kind":"official","path":"demo/utils.py","file_url":"https://github.com/felipemaiapolo/tinybenchmarks/blob/HEAD/demo/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfcec22b9dae71a3"}},{"code_sha256_prefix":"9562e2171d59db3a","entry":"get_commit_dates_models","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"generating_data/download_alpaca/preprocess_alpaca_eval.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/generating_data/download_alpaca/preprocess_alpaca_eval.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":"9562e2171d59db3a"}},{"code_sha256_prefix":"5c4864e2b480cdcb","entry":"get_last_commit_date","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"generating_data/download_alpaca/preprocess_alpaca_eval.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/generating_data/download_alpaca/preprocess_alpaca_eval.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":"5c4864e2b480cdcb"}},{"code_sha256_prefix":"68f19e5ceaec8296","entry":"get_random","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"selection.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/selection.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":"68f19e5ceaec8296"}},{"code_sha256_prefix":"479a232346a8cdc4","entry":"get_score_and_test_counts_from_sample","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"extract_data_from_logs.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/extract_data_from_logs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"479a232346a8cdc4"}},{"code_sha256_prefix":"6a02dcfbdb7bea7d","entry":"load_sample_ids","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"make_new_huggingface_dataset.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/make_new_huggingface_dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a02dcfbdb7bea7d"}},{"code_sha256_prefix":"9d2ac225248cfcc2","entry":"load_scores","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"plots.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/plots.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":"9d2ac225248cfcc2"}},{"code_sha256_prefix":"f81ca1d465c962aa","entry":"map_environments","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"get_docker_image_sizes.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/get_docker_image_sizes.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f81ca1d465c962aa"}},{"code_sha256_prefix":"d7d8fe87aefb67aa","entry":"merge_data_with_metadata","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"add_metadata_to_data.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/add_metadata_to_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7d8fe87aefb67aa"}},{"code_sha256_prefix":"a2fa41c1789608ea","entry":"merge_model_scores","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"extract_data_from_logs.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/extract_data_from_logs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2fa41c1789608ea"}},{"code_sha256_prefix":"ef12fdf35ff27c06","entry":"merge_with_environment_data","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"add_metadata_to_data.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/add_metadata_to_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef12fdf35ff27c06"}},{"code_sha256_prefix":"cc7ed1b21213f9b3","entry":"prepare_data","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"generate_subsets.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/generate_subsets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc7ed1b21213f9b3"}},{"code_sha256_prefix":"f20343e9cf5ded69","entry":"prepare_numeric_data","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"compare_subsets.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/compare_subsets.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f20343e9cf5ded69"}},{"code_sha256_prefix":"fb3c33baacb5cdd5","entry":"process_docker_output","repo":"mariushobbhahn/swebench-verified-mini","repo_kind":"listed","path":"get_docker_image_sizes.py","file_url":"https://github.com/mariushobbhahn/swebench-verified-mini/blob/HEAD/get_docker_image_sizes.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb3c33baacb5cdd5"}},{"code_sha256_prefix":"6620cc858a942cb4","entry":"run_adaptive_selection","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"selection.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/selection.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":"6620cc858a942cb4"}},{"code_sha256_prefix":"5c7d27e94d6596c8","entry":"select_initial_adaptive_items","repo":"felipemaiapolo/efficbench","repo_kind":"official","path":"selection.py","file_url":"https://github.com/felipemaiapolo/efficbench/blob/HEAD/selection.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":"5c7d27e94d6596c8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}