{"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/mmlu","name":"MML","full_name":"Massive Multitask Language Understanding","description_markdown":"**MMLU** (**Massive Multitask Language Understanding**) is a new benchmark designed to measure knowledge acquired during pretraining by evaluating models exclusively in zero-shot and few-shot settings. This makes the benchmark more challenging and more similar to how we evaluate humans. The benchmark covers 57 subjects across STEM, the humanities, the social sciences, and more. It ranges in difficulty from an elementary level to an advanced professional level, and it tests both world knowledge and problem solving ability. Subjects range from traditional areas, such as mathematics and history, to more specialized areas like law and ethics. The granularity and breadth of the subjects makes the benchmark ideal for identifying a model’s blind spots.\r\n\r\nImage source: [https://arxiv.org/pdf/2009.03300v3.pdf](https://arxiv.org/pdf/2009.03300v3.pdf)","description_withheld":null,"homepage":"https://github.com/hendrycks/test","introduced_date":"2020-09-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/measuring-massive-multitask-language","title":"Measuring Massive Multitask Language Understanding","first_author":"Dan Hendrycks","url":null},"license":{"name":"Custom","url":"https://github.com/hendrycks/test#citation"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Multiple Choice Question Answering (MCQA)","url":"/task/multiple-choice-qa","datasets_with_task":"/datasets/task/multiple-choice-qa"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"},{"name":"Multi-task Language Understanding","url":"/task/multi-task-language-understanding","datasets_with_task":"/datasets/task/multi-task-language-understanding"},{"name":"Single Choice Question","url":"/task/single-choice-question","datasets_with_task":"/datasets/task/single-choice-question"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["mmlu","MMLU TR v0.2","MMLU TR","MMLU (5-Shot)","MMLU (College Medicine)","MMLU (Professional medicine)","MMLU (Anatomy)","MMLU (Clinical Knowledge)","MMLU (Medical Genetics)","MMLU (Mathematics)","MMLU (Machine Learning)","MMLU (High School Statistics)","MMLU (High School Physics)","MMLU (High School Mathematics)","MMLU (High School Computer Science)","MMLU (High School Chemistry)","MMLU (High School Biology)","MMLU (Formal Logic)","MMLU (Elementary Mathematics)","MMLU (Electrical Engineer)","MMLU (Econometrics)","MMLU (College Physics)","MMLU (College Mathematics)","MMLU (College Computer Science)","MMLU (College Chemistry)","MMLU (College Biology)","MMLU (Astronomy)","MMLU (Abstract Algebra)","MML"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/hendrycks_test","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cais/mmlu","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/lighteval/mmlu","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Stevross/mmlu","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/swap-uniba/mmlu_ita","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Weyaxi/mmlu","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/justinphan3110/mmlu-test","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/justinphan3110/mmlu-test-2","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/neurotechnology/lt_mmlu","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/flunardelli/mmlu","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/rubricreward/llm-metric-mmlu","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1922,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset_variant":"MML","rows":44,"metrics":["Average (%)"],"first_row_in_archive_order":{"model":"GPT-4 o1(300b)","paper":"/paper/sieve-general-purpose-data-filtering-system","metrics":{"Average (%)":"87"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-11","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (College Biology)","rows":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Med-PaLM 2 (ER)","paper":"/paper/towards-expert-level-medical-question","metrics":{"Accuracy":"95.8"},"code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-8","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Medical Genetics)","rows":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Med-PaLM 2 (ER)","paper":"/paper/towards-expert-level-medical-question","metrics":{"Accuracy":"92"},"code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-25","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Professional medicine)","rows":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Med-PaLM 2 (5-shot)","paper":"/paper/towards-expert-level-medical-question","metrics":{"Accuracy":"95.2"},"code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-10","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Elementary Mathematics)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"41.5"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-12","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (High School Biology)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"80.3"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-13","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (College Chemistry)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"51"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-16","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (High School Mathematics)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GAL 120B (zero-shot)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"32.6"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-17","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Electrical Engineer)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GAL 120B (zero-shot)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"62.8"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-18","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (College Physics)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"46.1"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-2","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Formal Logic)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Gopher (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"35.7"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-20","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (High School Statistics)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"58.8"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-3","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Abstract Algebra)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GAL 30B (zero-shot)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"33.3"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-4","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Econometrics)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Gopher (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"43"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-5","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (High School Computer Science)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GAL 120B (zero-shot)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"70"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-7","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (College Mathematics)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GAL 120B (zero-shot)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"43"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-9","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Astronomy)","rows":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"73.0"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-14","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (High School Chemistry)","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"58.1"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-15","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (College Computer Science)","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"51.0"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-19","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (High School Physics)","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"36.4"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-6","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Machine Learning)","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla (few-shot, k=5)","paper":"/paper/galactica-a-large-language-model-for-science-1","metrics":{"Accuracy":"41.1"},"code_links":[{"title":"paperswithcode/galai","url":"https://github.com/paperswithcode/galai"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-23","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Clinical Knowledge)","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Med-PaLM 2 (ER)","paper":"/paper/towards-expert-level-medical-question","metrics":{"Accuracy":"88.7"},"code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-24","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (Anatomy)","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Med-PaLM 2 (ER)","paper":"/paper/towards-expert-level-medical-question","metrics":{"Accuracy":"84.4"},"code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-26","task":"Multiple Choice Question Answering (MCQA)","dataset_variant":"MMLU (College Medicine)","rows":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Med-PaLM (ER)","paper":"/paper/towards-expert-level-medical-question","metrics":{"Accuracy":"83.2"},"code_links":[{"title":"m42-health/med42","url":"https://github.com/m42-health/med42"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu-5-1","task":"Multi-task Language Understanding","dataset_variant":"MMLU (5-Shot)","rows":1,"metrics":["MMLU (5-shot)"],"first_row_in_archive_order":{"model":"Sakalti/ultiima-78B","paper":"/paper/merge-fast-private-text-generation","metrics":{"MMLU (5-shot)":"89.2"},"code_links":[{"title":"liangzid/MERGE","url":"https://github.com/liangzid/MERGE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-mmlu","task":"Question Answering","dataset_variant":"MML","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"qwen-LLM 7B","paper":"/paper/shakti-a-2-5-billion-parameter-small-language","metrics":{"Accuracy":"71.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-mmlu-5-shot","task":"Text Generation","dataset_variant":"MMLU (5-Shot)","rows":0,"metrics":["accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-mmlu-tr","task":"Text Generation","dataset_variant":"MMLU TR","rows":0,"metrics":["accuracy"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-mmlu-tr-v0-2","task":"Text Generation","dataset_variant":"MMLU TR v0.2","rows":0,"metrics":["accuracy"],"first_row_in_archive_order":null,"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":25,"of":25,"counts":{"papers_with_a_benchmark_row":25,"with_a_code_link":21,"where_syntology_ran_a_sample":13,"not_listed_spam_title":0,"listed":25,"listed_where_code_ran":13,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":13,"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/llama-3-meets-moe-efficient-upcycling","slug":"llama-3-meets-moe-efficient-upcycling","title":"Llama 3 Meets MoE: Efficient Upcycling","date":"2024-12-13","arxiv_id":"2412.09952","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sieve-general-purpose-data-filtering-system","slug":"sieve-general-purpose-data-filtering-system","title":"GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data","date":"2024-10-03","arxiv_id":"2410.02755","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-llama-3-herd-of-models","slug":"the-llama-3-herd-of-models","title":"The Llama 3 Herd of Models","date":"2024-07-31","arxiv_id":"2407.21783","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-llama-3-herd-of-models#ran","syntology_url":"https://syntology.ai/paper/2407.21783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21783"}}}},{"paper":"/paper/branch-train-mix-mixing-expert-llms-into-a","slug":"branch-train-mix-mixing-expert-llms-into-a","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","date":"2024-03-12","arxiv_id":"2403.07816","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","slug":"the-claude-3-model-family-opus-sonnet-haiku","title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","date":"2024-03-04","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mixtral-of-experts","slug":"mixtral-of-experts","title":"Mixtral of Experts","date":"2024-01-08","arxiv_id":"2401.04088","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}}}},{"paper":"/paper/the-falcon-series-of-open-language-models","slug":"the-falcon-series-of-open-language-models","title":"The Falcon Series of Open Language Models","date":"2023-11-28","arxiv_id":"2311.16867","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/infoentropy-loss-to-mitigate-bias-of-learning","slug":"infoentropy-loss-to-mitigate-bias-of-learning","title":"MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models","date":"2023-10-30","arxiv_id":"2310.19531","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"paper":"/paper/textbooks-are-all-you-need-ii-phi-1-5","slug":"textbooks-are-all-you-need-ii-phi-1-5","title":"Textbooks Are All You Need II: phi-1.5 technical report","date":"2023-09-11","arxiv_id":"2309.05463","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/biomedgpt-open-multimodal-generative-pre","slug":"biomedgpt-open-multimodal-generative-pre","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","date":"2023-08-18","arxiv_id":"2308.09442","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","rows_on_this_dataset":5,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":52,"samples_ran":33,"samples_constructed":7,"samples_ran_checked":20,"samples_ran_instrument_failed":13,"samples_unverified":19,"pointer_only_for_licence":20,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"paper":"/paper/merge-fast-private-text-generation","slug":"merge-fast-private-text-generation","title":"MERGE: Fast Private Text Generation","date":"2023-05-25","arxiv_id":"2305.15769","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-expert-level-medical-question","slug":"towards-expert-level-medical-question","title":"Towards Expert-Level Medical Question Answering with Large Language Models","date":"2023-05-16","arxiv_id":"2305.09617","rows_on_this_dataset":18,"code_links":1,"syntology":null},{"paper":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":3,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","rows_on_this_dataset":92,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"paper":"/paper/scaling-instruction-finetuned-language-models","slug":"scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","rows_on_this_dataset":9,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":8,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":7,"samples_unverified":9,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-instruction-finetuned-language-models#ran","syntology_url":"https://syntology.ai/paper/2210.11416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11416"}}}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glm-130b-an-open-bilingual-pre-trained-model#ran","syntology_url":"https://syntology.ai/paper/2210.02414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02414"}}}},{"paper":"/paper/few-shot-learning-with-retrieval-augmented","slug":"few-shot-learning-with-retrieval-augmented","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","date":"2022-08-05","arxiv_id":"2208.03299","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["facebookresearch/atlas"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/few-shot-learning-with-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2208.03299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03299"}}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}}}},{"paper":"/paper/gpt-neox-20b-an-open-source-autoregressive-1","slug":"gpt-neox-20b-an-open-source-autoregressive-1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","date":"2022-04-14","arxiv_id":"2204.06745","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["eleutherai/gpt-neox"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-neox-20b-an-open-source-autoregressive-1#ran","syntology_url":"https://syntology.ai/paper/2204.06745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06745"}}}},{"paper":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":8,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/llama-3-meets-moe-efficient-upcycling","slug":"llama-3-meets-moe-efficient-upcycling","title":"Llama 3 Meets MoE: Efficient Upcycling","date":"2024-12-13","arxiv_id":"2412.09952","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sieve-general-purpose-data-filtering-system","slug":"sieve-general-purpose-data-filtering-system","title":"GPT-4o as the Gold Standard: A Scalable and General Purpose Approach to Filter Language Model Pretraining Data","date":"2024-10-03","arxiv_id":"2410.02755","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-llama-3-herd-of-models","slug":"the-llama-3-herd-of-models","title":"The Llama 3 Herd of Models","date":"2024-07-31","arxiv_id":"2407.21783","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/the-llama-3-herd-of-models#ran","syntology_url":"https://syntology.ai/paper/2407.21783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21783"}}}},{"paper":"/paper/branch-train-mix-mixing-expert-llms-into-a","slug":"branch-train-mix-mixing-expert-llms-into-a","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","date":"2024-03-12","arxiv_id":"2403.07816","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","slug":"the-claude-3-model-family-opus-sonnet-haiku","title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","date":"2024-03-04","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mixtral-of-experts","slug":"mixtral-of-experts","title":"Mixtral of Experts","date":"2024-01-08","arxiv_id":"2401.04088","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":5,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}}}},{"paper":"/paper/the-falcon-series-of-open-language-models","slug":"the-falcon-series-of-open-language-models","title":"The Falcon Series of Open Language Models","date":"2023-11-28","arxiv_id":"2311.16867","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/infoentropy-loss-to-mitigate-bias-of-learning","slug":"infoentropy-loss-to-mitigate-bias-of-learning","title":"MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models","date":"2023-10-30","arxiv_id":"2310.19531","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"paper":"/paper/textbooks-are-all-you-need-ii-phi-1-5","slug":"textbooks-are-all-you-need-ii-phi-1-5","title":"Textbooks Are All You Need II: phi-1.5 technical report","date":"2023-09-11","arxiv_id":"2309.05463","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/biomedgpt-open-multimodal-generative-pre","slug":"biomedgpt-open-multimodal-generative-pre","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","date":"2023-08-18","arxiv_id":"2308.09442","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","rows_on_this_dataset":5,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":52,"samples_ran":33,"samples_constructed":7,"samples_ran_checked":20,"samples_ran_instrument_failed":13,"samples_unverified":19,"pointer_only_for_licence":20,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"paper":"/paper/merge-fast-private-text-generation","slug":"merge-fast-private-text-generation","title":"MERGE: Fast Private Text Generation","date":"2023-05-25","arxiv_id":"2305.15769","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/towards-expert-level-medical-question","slug":"towards-expert-level-medical-question","title":"Towards Expert-Level Medical Question Answering with Large Language Models","date":"2023-05-16","arxiv_id":"2305.09617","rows_on_this_dataset":18,"code_links":1,"syntology":null},{"paper":"/paper/bloomberggpt-a-large-language-model-for","slug":"bloomberggpt-a-large-language-model-for","title":"BloombergGPT: A Large Language Model for Finance","date":"2023-03-30","arxiv_id":"2303.17564","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":3,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/galactica-a-large-language-model-for-science-1","slug":"galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","date":"2022-11-16","arxiv_id":"2211.09085","rows_on_this_dataset":92,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["paperswithcode/galai"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/galactica-a-large-language-model-for-science-1#ran","syntology_url":"https://syntology.ai/paper/2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}}}},{"paper":"/paper/scaling-instruction-finetuned-language-models","slug":"scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","rows_on_this_dataset":9,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":8,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":7,"samples_unverified":9,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scaling-instruction-finetuned-language-models#ran","syntology_url":"https://syntology.ai/paper/2210.11416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11416"}}}},{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","slug":"glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","arxiv_id":"2210.02414","rows_on_this_dataset":1,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":21,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":14,"samples_ran_instrument_failed":1,"samples_unverified":6,"pointer_only_for_licence":0,"official":{"repos":["thudm/glm-130b"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/glm-130b-an-open-bilingual-pre-trained-model#ran","syntology_url":"https://syntology.ai/paper/2210.02414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02414"}}}},{"paper":"/paper/few-shot-learning-with-retrieval-augmented","slug":"few-shot-learning-with-retrieval-augmented","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","date":"2022-08-05","arxiv_id":"2208.03299","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["facebookresearch/atlas"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/few-shot-learning-with-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2208.03299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03299"}}}},{"paper":"/paper/unifying-language-learning-paradigms","slug":"unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":15,"samples_constructed":0,"samples_ran_checked":15,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-language-learning-paradigms#ran","syntology_url":"https://syntology.ai/paper/2205.05131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05131"}}}},{"paper":"/paper/gpt-neox-20b-an-open-source-autoregressive-1","slug":"gpt-neox-20b-an-open-source-autoregressive-1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","date":"2022-04-14","arxiv_id":"2204.06745","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["eleutherai/gpt-neox"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-neox-20b-an-open-source-autoregressive-1#ran","syntology_url":"https://syntology.ai/paper/2204.06745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06745"}}}},{"paper":"/paper/training-compute-optimal-large-language","slug":"training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":8,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":4,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}}}}],"papers_where_code_ran":13,"papers_where_code_ran_first_page":"/dataset/mmlu/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/mmlu/papers/ran/1","json":"/dataset/mmlu/papers/ran/1.json","rows":13}],"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":13,"samples_harvested":212,"samples_ran":151,"samples_constructed":25,"samples_ran_checked":113,"samples_ran_instrument_failed":38,"samples_unverified":61,"pointer_only_for_licence":35,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":13,"papers_with_a_run_with_no_instrument_failure":13,"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":82,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","since_archive":"/sota/multi-task-language-understanding-on-mmlu#since-judged","papers_judged":59,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-11","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-11#since-judged","papers_judged":5,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-8","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-8#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-25","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-25#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-2","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-2#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-3","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-3#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-4","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-4#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-5","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-5#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-7","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-7#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-9","since_archive":"/sota/multiple-choice-question-answering-mcqa-on-9#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu-5-1","since_archive":"/sota/multi-task-language-understanding-on-mmlu-5-1#since-judged","papers_judged":16,"placed":0}]},"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":"3207ea675f723bd693217763f56aa62f9da2043371bf54e46260599d0950631a","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}