{"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/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","arxiv_id":"2112.11446","date":"2021-12-08","proceeding":"NA 2021 12","authors":["Jack W. Rae","Sebastian Borgeaud","Trevor Cai","Katie Millican","Jordan Hoffmann","Francis Song","John Aslanides","Sarah Henderson","Roman Ring","Susannah Young","Eliza Rutherford","Tom Hennigan","Jacob Menick","Albin Cassirer","Richard Powell","George van den Driessche","Lisa Anne Hendricks","Maribeth Rauh","Po-Sen Huang","Amelia Glaese","Johannes Welbl","Sumanth Dathathri","Saffron Huang","Jonathan Uesato","John Mellor","Irina Higgins","Antonia Creswell","Nat McAleese","Amy Wu","Erich Elsen","Siddhant Jayakumar","Elena Buchatskaya","David Budden","Esme Sutherland","Karen Simonyan","Michela Paganini","Laurent SIfre","Lena Martens","Xiang Lorraine Li","Adhiguna Kuncoro","Aida Nematzadeh","Elena Gribovskaya","Domenic Donato","Angeliki Lazaridou","Arthur Mensch","Jean-Baptiste Lespiau","Maria Tsimpoukelli","Nikolai Grigorev","Doug Fritz","Thibault Sottiaux","Mantas Pajarskas","Toby Pohlen","Zhitao Gong","Daniel Toyama","Cyprien de Masson d'Autume","Yujia Li","Tayfun Terzi","Vladimir Mikulik","Igor Babuschkin","Aidan Clark","Diego de Las Casas","Aurelia Guy","Chris Jones","James Bradbury","Matthew Johnson","Blake Hechtman","Laura Weidinger","Iason Gabriel","William Isaac","Ed Lockhart","Simon Osindero","Laura Rimell","Chris Dyer","Oriol Vinyals","Kareem Ayoub","Jeff Stanway","Lorrayne Bennett","Demis Hassabis","Koray Kavukcuoglu","Geoffrey Irving"],"abstract":"Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis of Transformer-based language model performance across a wide range of model scales -- from models with tens of millions of parameters up to a 280 billion parameter model called Gopher. These models are evaluated on 152 diverse tasks, achieving state-of-the-art performance across the majority. Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language, but logical and mathematical reasoning see less benefit. We provide a holistic analysis of the training dataset and model's behaviour, covering the intersection of model scale with bias and toxicity. Finally we discuss the application of language models to AI safety and the mitigation of downstream harms.","url_abs":"https://arxiv.org/abs/2112.11446v2","url_pdf":"https://arxiv.org/pdf/2112.11446v2.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":"scaling-language-models-methods-analysis-1","repo_url":"https://github.com/allenai/dolma","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"scaling-language-models-methods-analysis-1","repo_url":"https://github.com/bramiozo/PubScience","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"scaling-language-models-methods-analysis-1","repo_url":"https://github.com/rvlopes/gloria","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"abstract-algebra","task_name":"Abstract Algebra"},{"task_slug":"anachronisms","task_name":"Anachronisms"},{"task_slug":"analogical-similarity","task_name":"Analogical Similarity"},{"task_slug":"analytic-entailment","task_name":"Analytic Entailment"},{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"astronomy","task_name":"Astronomy"},{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"business-ethics","task_name":"Business Ethics"},{"task_slug":"causal-judgment","task_name":"Causal Judgment"},{"task_slug":"checkmate-in-one","task_name":"Checkmate In One"},{"task_slug":"clinical-knowledge","task_name":"Clinical Knowledge"},{"task_slug":"code-line-descriptions","task_name":"Code Line Descriptions"},{"task_slug":"college-biology","task_name":"College Biology"},{"task_slug":"college-chemistry","task_name":"College Chemistry"},{"task_slug":"college-computer-science","task_name":"College Computer Science"},{"task_slug":"college-mathematics","task_name":"College Mathematics"},{"task_slug":"college-medicine","task_name":"College Medicine"},{"task_slug":"college-physics","task_name":"College Physics"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"computer-security","task_name":"Computer Security"},{"task_slug":"conceptual-physics","task_name":"Conceptual Physics"},{"task_slug":"crash-blossom","task_name":"Crash Blossom"},{"task_slug":"crass-ai","task_name":"Crass AI"},{"task_slug":"dark-humor-detection","task_name":"Dark Humor Detection"},{"task_slug":"date-understanding","task_name":"Date Understanding"},{"task_slug":"disambiguation-qa","task_name":"Disambiguation QA"},{"task_slug":"discourse-marker-prediction","task_name":"Discourse Marker Prediction"},{"task_slug":"econometrics","task_name":"Econometrics"},{"task_slug":"electrical-engineering","task_name":"Electrical Engineering"},{"task_slug":"elementary-mathematics","task_name":"Elementary Mathematics"},{"task_slug":"emotional-intelligence","task_name":"Emotional Intelligence"},{"task_slug":"empirical-judgments","task_name":"Empirical Judgments"},{"task_slug":"english-proverbs","task_name":"English Proverbs"},{"task_slug":"entailed-polarity","task_name":"Entailed Polarity"},{"task_slug":"epistemic-reasoning","task_name":"Epistemic Reasoning"},{"task_slug":"ethics","task_name":"Ethics"},{"task_slug":"evaluating-information-essentiality","task_name":"Evaluating Information Essentiality"},{"task_slug":"fever-2-way","task_name":"FEVER (2-way)"},{"task_slug":"fever-3-way","task_name":"FEVER (3-way)"},{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"fantasy-reasoning","task_name":"Fantasy Reasoning"},{"task_slug":"figure-of-speech-detection","task_name":"Figure Of Speech Detection"},{"task_slug":"formal-fallacies-syllogisms-negation","task_name":"Formal Fallacies Syllogisms Negation"},{"task_slug":"formal-logic","task_name":"Formal Logic"},{"task_slug":"gre-reading-comprehension","task_name":"GRE Reading Comprehension"},{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"global-facts","task_name":"Global Facts"},{"task_slug":"hellaswag","task_name":"HellaSwag"},{"task_slug":"high-school-biology","task_name":"High School Biology"},{"task_slug":"high-school-chemistry","task_name":"High School Chemistry"},{"task_slug":"high-school-computer-science","task_name":"High School Computer Science"},{"task_slug":"high-school-european-history","task_name":"High School European History"},{"task_slug":"high-school-geography","task_name":"High School Geography"},{"task_slug":"high-school-government-and-politics","task_name":"High School Government and Politics"},{"task_slug":"high-school-macroeconomics","task_name":"High School Macroeconomics"},{"task_slug":"high-school-mathematics","task_name":"High School Mathematics"},{"task_slug":"high-school-microeconomics","task_name":"High School Microeconomics"},{"task_slug":"high-school-physics","task_name":"High School Physics"},{"task_slug":"high-school-psychology","task_name":"High School Psychology"},{"task_slug":"high-school-statistics","task_name":"High School Statistics"},{"task_slug":"high-school-us-history","task_name":"High School US History"},{"task_slug":"high-school-world-history","task_name":"High School World History"},{"task_slug":"hindu-knowledge","task_name":"Hindu Knowledge"},{"task_slug":"human-aging","task_name":"Human Aging"},{"task_slug":"human-organs-senses-multiple-choice","task_name":"Human Organs Senses Multiple Choice"},{"task_slug":"human-sexuality","task_name":"Human Sexuality"},{"task_slug":"hyperbaton","task_name":"Hyperbaton"},{"task_slug":"identify-odd-metapor","task_name":"Identify Odd Metapor"},{"task_slug":"implicatures","task_name":"Implicatures"},{"task_slug":"implicit-relations","task_name":"Implicit Relations"},{"task_slug":"intelligent-communication","task_name":"Intelligent Communication"},{"task_slug":"intent-recognition","task_name":"Intent Recognition"},{"task_slug":"international-law","task_name":"International Law"},{"task_slug":"irony-identification","task_name":"Irony Identification"},{"task_slug":"jurisprudence","task_name":"Jurisprudence"},{"task_slug":"known-unknowns","task_name":"Known Unknowns"},{"task_slug":"lambada","task_name":"LAMBADA"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"logic-grid-puzzle","task_name":"Logic Grid Puzzle"},{"task_slug":"logical-args","task_name":"Logical Args"},{"task_slug":"logical-fallacies","task_name":"Logical Fallacies"},{"task_slug":"logical-fallacy-detection","task_name":"Logical Fallacy Detection"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"logical-sequence","task_name":"Logical Sequence"},{"task_slug":"management","task_name":"Management"},{"task_slug":"marketing","task_name":"Marketing"},{"task_slug":"mathematical-induction","task_name":"Mathematical Induction"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"medical-genetics","task_name":"Medical Genetics"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"metaphor-boolean","task_name":"Metaphor Boolean"},{"task_slug":"miscellaneous","task_name":"Miscellaneous"},{"task_slug":"misconceptions","task_name":"Misconceptions"},{"task_slug":"moral-disputes","task_name":"Moral Disputes"},{"task_slug":"moral-permissibility","task_name":"Moral Permissibility"},{"task_slug":"moral-scenarios","task_name":"Moral Scenarios"},{"task_slug":"movie-dialog-same-or-different","task_name":"Movie Dialog Same Or Different"},{"task_slug":null,"task_name":"Movie Genre Recommendation System"},{"task_slug":"movie-recommendation","task_name":"Movie Recommendation"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"},{"task_slug":"multiple-choice-qa","task_name":"Multiple Choice Question Answering (MCQA)"},{"task_slug":"natural-questions","task_name":"Natural Questions"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"nonsense-words-grammar","task_name":"Nonsense Words Grammar"},{"task_slug":"novel-concepts","task_name":"Novel Concepts"},{"task_slug":"nutrition","task_name":"Nutrition"},{"task_slug":"odd-one-out","task_name":"Odd One Out"},{"task_slug":"penguins-in-a-table","task_name":"Penguins In A Table"},{"task_slug":"philosophy","task_name":"Philosophy"},{"task_slug":"phrase-relatedness","task_name":"Phrase Relatedness"},{"task_slug":"physical-intuition","task_name":"Physical Intuition"},{"task_slug":"physics-mc","task_name":"Physics MC"},{"task_slug":"prehistory","task_name":"Prehistory"},{"task_slug":"presuppositions-as-nli","task_name":"Presuppositions As NLI"},{"task_slug":"professional-accounting","task_name":"Professional Accounting"},{"task_slug":"professional-law","task_name":"Professional Law"},{"task_slug":"professional-medicine","task_name":"Professional Medicine"},{"task_slug":"professional-psychology","task_name":"Professional Psychology"},{"task_slug":"public-relations","task_name":"Public Relations"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"question-selection","task_name":"Question Selection"},{"task_slug":"race-h","task_name":"RACE-h"},{"task_slug":"race-m","task_name":"RACE-m"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"reasoning-about-colored-objects","task_name":"Reasoning About Colored Objects"},{"task_slug":"riddle-sense","task_name":"Riddle Sense"},{"task_slug":"ruin-names","task_name":"Ruin Names"},{"task_slug":"snarks","task_name":"SNARKS"},{"task_slug":"sarcasm-detection","task_name":"Sarcasm Detection"},{"task_slug":"security-studies","task_name":"Security Studies"},{"task_slug":"sentence-ambiguity","task_name":"Sentence Ambiguity"},{"task_slug":"sentence-completion","task_name":"Sentence Completion"},{"task_slug":"similarities-abstraction","task_name":"Similarities Abstraction"},{"task_slug":"sociology","task_name":"Sociology"},{"task_slug":"sports-understanding","task_name":"Sports Understanding"},{"task_slug":"strategyqa","task_name":"StrategyQA"},{"task_slug":"temporal-sequences","task_name":"Temporal Sequences"},{"task_slug":"timedial","task_name":"Timedial"},{"task_slug":"triviaqa","task_name":"TriviaQA"},{"task_slug":"us-foreign-policy","task_name":"US Foreign Policy"},{"task_slug":"understanding-fables","task_name":"Understanding Fables"},{"task_slug":"virology","task_name":"Virology"},{"task_slug":"winogrande","task_name":"Winogrande"},{"task_slug":"winowhy","task_name":"Winowhy"},{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"},{"task_slug":"world-religions","task_name":"World Religions"}],"methods":[],"datasets_introduced":[{"slug":"massivetext","name":"MassiveText","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/abstract-algebra-on-big-bench","task":"Abstract Algebra","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"25.0"},"uses_additional_data":false},{"leaderboard":"/sota/analogical-similarity-on-big-bench","task":"Analogical Similarity","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"17.2"},"uses_additional_data":false},{"leaderboard":"/sota/analytic-entailment-on-big-bench","task":"Analytic Entailment","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"53.0"},"uses_additional_data":false},{"leaderboard":"/sota/anatomy-on-big-bench","task":"Anatomy","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"56.3"},"uses_additional_data":false},{"leaderboard":"/sota/astronomy-on-big-bench","task":"Astronomy","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"65.8"},"uses_additional_data":false},{"leaderboard":"/sota/machine-learning-on-big-bench","task":"BIG-bench Machine Learning","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"41.1"},"uses_additional_data":false},{"leaderboard":"/sota/business-ethics-on-big-bench","task":"Business Ethics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/clinical-knowledge-on-big-bench","task":"Clinical Knowledge","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"67.2"},"uses_additional_data":false},{"leaderboard":"/sota/college-mathematics-on-big-bench","task":"College Mathematics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"37.0"},"uses_additional_data":true},{"leaderboard":"/sota/college-medicine-on-big-bench","task":"College Medicine","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"60.1"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-causal","task":"Common Sense Reasoning","dataset":"BIG-bench (Causal Judgment)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":8,"of":9,"metrics":{"Accuracy":"50.8"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-date","task":"Common Sense Reasoning","dataset":"BIG-bench (Date Understanding)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"44.1"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench","task":"Common Sense Reasoning","dataset":"BIG-bench (Disambiguation QA)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"45.5"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-known","task":"Common Sense Reasoning","dataset":"BIG-bench (Known Unknowns)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"63.6"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-logical","task":"Common Sense Reasoning","dataset":"BIG-bench (Logical Sequence)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-sports","task":"Common Sense Reasoning","dataset":"BIG-bench (Sports Understanding)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":6,"of":8,"metrics":{"Accuracy":"54.9"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-big-bench-winowhy","task":"Common Sense Reasoning","dataset":"BIG-bench (Winowhy)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"56.7"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"Gopher 280B (0-shot)","rank_in_archive_order":40,"of":77,"metrics":{"Accuracy":"70.1"},"uses_additional_data":false},{"leaderboard":"/sota/computer-security-on-big-bench","task":"Computer Security","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"65.0"},"uses_additional_data":false},{"leaderboard":"/sota/crash-blossom-on-big-bench","task":"Crash Blossom","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy ":"63.6"},"uses_additional_data":false},{"leaderboard":"/sota/crass-ai-on-big-bench","task":"Crass AI","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"56.8"},"uses_additional_data":false},{"leaderboard":"/sota/dark-humor-detection-on-big-bench","task":"Dark Humor Detection","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"83.1"},"uses_additional_data":false},{"leaderboard":"/sota/discourse-marker-prediction-on-big-bench","task":"Discourse Marker Prediction","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"11.7"},"uses_additional_data":false},{"leaderboard":"/sota/econometrics-on-big-bench","task":"Econometrics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"43"},"uses_additional_data":false},{"leaderboard":"/sota/elementary-mathematics-on-big-bench","task":"Elementary Mathematics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"33.6"},"uses_additional_data":false},{"leaderboard":"/sota/empirical-judgments-on-big-bench","task":"Empirical Judgments","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"52.5"},"uses_additional_data":false},{"leaderboard":"/sota/english-proverbs-on-big-bench","task":"English Proverbs","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/entailed-polarity-on-big-bench","task":"Entailed Polarity","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"89.5"},"uses_additional_data":false},{"leaderboard":"/sota/epistemic-reasoning-on-big-bench","task":"Epistemic Reasoning","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"56.4"},"uses_additional_data":false},{"leaderboard":"/sota/evaluating-information-essentiality-on-big","task":"Evaluating Information Essentiality","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"16.7"},"uses_additional_data":false},{"leaderboard":"/sota/fever-2-way-on-big-bench","task":"FEVER (2-way)","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=10)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"77.5"},"uses_additional_data":false},{"leaderboard":"/sota/fever-3-way-on-big-bench","task":"FEVER (3-way)","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=15)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"77.5"},"uses_additional_data":false},{"leaderboard":"/sota/fantasy-reasoning-on-big-bench","task":"Fantasy Reasoning","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"64.1"},"uses_additional_data":false},{"leaderboard":"/sota/figure-of-speech-detection-on-big-bench","task":"Figure Of Speech Detection","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"52.7"},"uses_additional_data":false},{"leaderboard":"/sota/formal-logic-on-big-bench","task":"Formal Logic","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"35.7"},"uses_additional_data":false},{"leaderboard":"/sota/gre-reading-comprehension-on-big-bench","task":"GRE Reading Comprehension","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"27.3"},"uses_additional_data":false},{"leaderboard":"/sota/general-knowledge-on-big-bench","task":"General Knowledge","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"93.9"},"uses_additional_data":false},{"leaderboard":"/sota/global-facts-on-big-bench","task":"Global Facts","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"38.0"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-european-history-on-big-bench","task":"High School European History","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"72.1"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-geography-on-big-bench","task":"High School Geography","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"76.8"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-government-and-politics-on-big","task":"High School Government and Politics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"83.9"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-macroeconomics-on-big-bench","task":"High School Macroeconomics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"65.1"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-mathematics-on-big-bench","task":"High School Mathematics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"23.7"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-microeconomics-on-big-bench","task":"High School Microeconomics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"66.4"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-psychology-on-big-bench","task":"High School Psychology","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-us-history-on-big-bench","task":"High School US History","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"78.9"},"uses_additional_data":false},{"leaderboard":"/sota/high-school-world-history-on-big-bench","task":"High School World History","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"75.1"},"uses_additional_data":false},{"leaderboard":"/sota/human-aging-on-big-bench","task":"Human Aging","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"66.4"},"uses_additional_data":false},{"leaderboard":"/sota/human-organs-senses-multiple-choice-on-big","task":"Human Organs Senses Multiple Choice","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"84.8"},"uses_additional_data":false},{"leaderboard":"/sota/human-sexuality-on-big-bench","task":"Human Sexuality","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"67.2"},"uses_additional_data":false},{"leaderboard":"/sota/identify-odd-metapor-on-big-bench","task":"Identify Odd Metapor","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"38.6"},"uses_additional_data":false},{"leaderboard":"/sota/implicatures-on-big-bench","task":"Implicatures","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"62.0"},"uses_additional_data":false},{"leaderboard":"/sota/implicit-relations-on-big-bench","task":"Implicit Relations","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/intent-recognition-on-big-bench","task":"Intent Recognition","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"88.7"},"uses_additional_data":false},{"leaderboard":"/sota/international-law-on-big-bench","task":"International Law","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"77.7"},"uses_additional_data":false},{"leaderboard":"/sota/irony-identification-on-big-bench","task":"Irony Identification","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"69.7"},"uses_additional_data":false},{"leaderboard":"/sota/jurisprudence-on-big-bench","task":"Jurisprudence","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"71.3"},"uses_additional_data":false},{"leaderboard":"/sota/lambada-on-big-bench","task":"LAMBADA","dataset":"BIG-bench","model":"Gopher-280B (zero-shot)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"74.5"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-arxiv","task":"Language Modelling","dataset":"Arxiv HEP-TH citation graph","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.662"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-bookcorpus2","task":"Language Modelling","dataset":"Bookcorpus2","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.741"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-books3","task":"Language Modelling","dataset":"Books3","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.712"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-curation-corpus","task":"Language Modelling","dataset":"Curation Corpus","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.475"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-dm-mathematics","task":"Language Modelling","dataset":"DM Mathematics","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"1.14"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-freelaw","task":"Language Modelling","dataset":"FreeLaw","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.513"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-github","task":"Language Modelling","dataset":"GitHub","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.377"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-gutenberg-pg-19","task":"Language Modelling","dataset":"Gutenberg PG-19","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.656"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-hackernews","task":"Language Modelling","dataset":"HackerNews","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.890"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-nih-exporter","task":"Language Modelling","dataset":"NIH ExPorter","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.590"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-opensubtitles","task":"Language Modelling","dataset":"OpenSubtitles","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.899"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-openwebtext2","task":"Language Modelling","dataset":"OpenWebtext2","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.677"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-philpapers","task":"Language Modelling","dataset":"PhilPapers","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.695"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-pile-cc","task":"Language Modelling","dataset":"Pile CC","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.691"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-pubmed-central","task":"Language Modelling","dataset":"PubMed Central","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.525"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-pubmed-abstracts","task":"Language Modelling","dataset":"PubMed Cognitive Control Abstracts","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.577"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-stackexchange","task":"Language Modelling","dataset":"StackExchange","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.641"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-uspto-backgrounds","task":"Language Modelling","dataset":"USPTO Backgrounds","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"0.546"},"uses_additional_data":false},{"leaderboard":"/sota/language-modelling-on-ubuntu-irc","task":"Language Modelling","dataset":"Ubuntu IRC","model":"Gopher","rank_in_archive_order":1,"of":1,"metrics":{"BPB":"1.09"},"uses_additional_data":false},{"leaderboard":"/sota/logical-args-on-big-bench","task":"Logical Args","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy ":"59.1"},"uses_additional_data":false},{"leaderboard":"/sota/logical-fallacies-on-big-bench","task":"Logical Fallacies","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/logical-reasoning-on-big-bench-formal","task":"Logical Reasoning","dataset":"BIG-bench (Formal Fallacies Syllogisms Negation)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"50.7"},"uses_additional_data":false},{"leaderboard":"/sota/logical-reasoning-on-big-bench-logic-grid","task":"Logical Reasoning","dataset":"BIG-bench (Logic Grid Puzzle)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"35.1"},"uses_additional_data":false},{"leaderboard":"/sota/logical-reasoning-on-big-bench-logical","task":"Logical Reasoning","dataset":"BIG-bench (Logical Fallacy Detection)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/logical-reasoning-on-big-bench-penguins-in-a","task":"Logical Reasoning","dataset":"BIG-bench (Penguins In A Table)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"40.6"},"uses_additional_data":false},{"leaderboard":"/sota/logical-reasoning-on-big-bench-reasoning","task":"Logical Reasoning","dataset":"BIG-bench (Reasoning About Colored Objects)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"49.2"},"uses_additional_data":false},{"leaderboard":"/sota/logical-reasoning-on-big-bench-strategyqa","task":"Logical Reasoning","dataset":"BIG-bench (StrategyQA)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"61.0"},"uses_additional_data":false},{"leaderboard":"/sota/logical-reasoning-on-big-bench-temporal","task":"Logical Reasoning","dataset":"BIG-bench (Temporal Sequences)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"19.0"},"uses_additional_data":false},{"leaderboard":"/sota/management-on-big-bench","task":"Management","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"77.7"},"uses_additional_data":false},{"leaderboard":"/sota/marketing-on-big-bench","task":"Marketing","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"83.3"},"uses_additional_data":false},{"leaderboard":"/sota/mathematical-induction-on-big-bench","task":"Mathematical Induction","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy ":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/medical-genetics-on-big-bench","task":"Medical Genetics","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"69.0"},"uses_additional_data":false},{"leaderboard":"/sota/memorization-on-big-bench-hindu-knowledge","task":"Memorization","dataset":"BIG-bench (Hindu Knowledge)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"80"},"uses_additional_data":false},{"leaderboard":"/sota/metaphor-boolean-on-big-bench","task":"Metaphor Boolean","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"59.3"},"uses_additional_data":false},{"leaderboard":"/sota/miscellaneous-on-big-bench","task":"Miscellaneous","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"75.7"},"uses_additional_data":false},{"leaderboard":"/sota/misconceptions-on-big-bench","task":"Misconceptions","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"61.7"},"uses_additional_data":false},{"leaderboard":"/sota/moral-disputes-on-big-bench","task":"Moral Disputes","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"66.8"},"uses_additional_data":false},{"leaderboard":"/sota/moral-permissibility-on-big-bench","task":"Moral Permissibility","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"55.1"},"uses_additional_data":false},{"leaderboard":"/sota/moral-scenarios-on-big-bench","task":"Moral Scenarios","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"40.2"},"uses_additional_data":false},{"leaderboard":"/sota/movie-dialog-same-or-different-on-big-bench","task":"Movie Dialog Same Or Different","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"50.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-27","task":"Multiple Choice Question Answering (MCQA)","dataset":"BIG-bench (Hyperbaton)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"51.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-28","task":"Multiple Choice Question Answering (MCQA)","dataset":"BIG-bench (Movie Recommendation)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"50.5"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-29","task":"Multiple Choice Question Answering (MCQA)","dataset":"BIG-bench (Navigate)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":5,"of":9,"metrics":{"Accuracy":"51.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-31","task":"Multiple Choice Question Answering (MCQA)","dataset":"BIG-bench (Novel Concepts)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"59.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-30","task":"Multiple Choice Question Answering (MCQA)","dataset":"BIG-bench (Ruin Names)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":9,"of":9,"metrics":{"Accuracy":"38.6"},"uses_additional_data":false},{"leaderboard":"/sota/natural-questions-on-big-bench","task":"Natural Questions","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=64)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"28.2"},"uses_additional_data":false},{"leaderboard":"/sota/nonsense-words-grammar-on-big-bench","task":"Nonsense Words Grammar","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"61.4"},"uses_additional_data":false},{"leaderboard":"/sota/nutrition-on-big-bench","task":"Nutrition","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"69.9"},"uses_additional_data":false},{"leaderboard":"/sota/odd-one-out-on-big-bench","task":"Odd One Out","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"32.5"},"uses_additional_data":false},{"leaderboard":"/sota/philosophy-on-big-bench","task":"Philosophy","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"68.8"},"uses_additional_data":false},{"leaderboard":"/sota/phrase-relatedness-on-big-bench","task":"Phrase Relatedness","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/physical-intuition-on-big-bench","task":"Physical Intuition","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"59.7"},"uses_additional_data":false},{"leaderboard":"/sota/prehistory-on-big-bench","task":"Prehistory","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"67.6"},"uses_additional_data":false},{"leaderboard":"/sota/presuppositions-as-nli-on-big-bench","task":"Presuppositions As NLI","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"34.0"},"uses_additional_data":false},{"leaderboard":"/sota/professional-accounting-on-big-bench","task":"Professional Accounting","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"44.3"},"uses_additional_data":false},{"leaderboard":"/sota/professional-law-on-big-bench","task":"Professional Law","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"44.5"},"uses_additional_data":false},{"leaderboard":"/sota/professional-medicine-on-big-bench","task":"Professional Medicine","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"64.0"},"uses_additional_data":false},{"leaderboard":"/sota/professional-psychology-on-big-bench","task":"Professional Psychology","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"68.1"},"uses_additional_data":false},{"leaderboard":"/sota/public-relations-on-big-bench","task":"Public Relations","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"71.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-boolq","task":"Question Answering","dataset":"BoolQ","model":"Gopher (zero-shot)","rank_in_archive_order":28,"of":65,"metrics":{"Accuracy":"79.3"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-natural-questions","task":"Question Answering","dataset":"Natural Questions","model":"Gopher (few-shot, k=64)","rank_in_archive_order":38,"of":47,"metrics":{"EM":"28.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"Gopher 280B (0-shot)","rank_in_archive_order":25,"of":67,"metrics":{"Accuracy":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-social-iqa","task":"Question Answering","dataset":"SIQA","model":"Gopher (zero-shot)","rank_in_archive_order":20,"of":24,"metrics":{"Accuracy":"50.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"Gopher 280B (zero-shot, Our Prompt + Choices)","rank_in_archive_order":8,"of":33,"metrics":{"MC1":"0.295"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"Gopher 7.1 (zero-shot, QA prompts)","rank_in_archive_order":11,"of":33,"metrics":{"MC1":"0.25"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"Gopher 7.1B (zero-shot, Our Prompt + Choices)","rank_in_archive_order":13,"of":33,"metrics":{"MC1":"0.23"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"Gopher 1.4 (zero-shot, QA prompts)","rank_in_archive_order":14,"of":33,"metrics":{"MC1":"0.23"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"Gopher 1.4B (zero-shot, Our Prompt + Choices)","rank_in_archive_order":16,"of":33,"metrics":{"MC1":"0.217"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"Gopher 280B (zero-shot, QA prompts)","rank_in_archive_order":24,"of":33,"metrics":{"MC1":"0. 27"},"uses_additional_data":false},{"leaderboard":"/sota/question-selection-on-big-bench","task":"Question Selection","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"41.4"},"uses_additional_data":false},{"leaderboard":"/sota/race-h-on-big-bench","task":"RACE-h","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"71.6"},"uses_additional_data":false},{"leaderboard":"/sota/race-m-on-big-bench","task":"RACE-m","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"75.1"},"uses_additional_data":false},{"leaderboard":"/sota/riddle-sense-on-big-bench","task":"Riddle Sense","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"68.2"},"uses_additional_data":false},{"leaderboard":"/sota/sarcasm-detection-on-big-bench-snarks","task":"Sarcasm Detection","dataset":"BIG-bench (SNARKS)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":8,"of":8,"metrics":{"Accuracy":"48.3"},"uses_additional_data":false},{"leaderboard":"/sota/security-studies-on-big-bench","task":"Security Studies","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"64.9"},"uses_additional_data":false},{"leaderboard":"/sota/sentence-ambiguity-on-big-bench","task":"Sentence Ambiguity","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"69.1"},"uses_additional_data":false},{"leaderboard":"/sota/sentence-completion-on-hellaswag","task":"Sentence Completion","dataset":"HellaSwag","model":"Gopher 280B (0-shot)","rank_in_archive_order":46,"of":89,"metrics":{"Accuracy":"79.2"},"uses_additional_data":false},{"leaderboard":"/sota/similarities-abstraction-on-big-bench","task":"Similarities Abstraction","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/sociology-on-big-bench","task":"Sociology","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"84.1"},"uses_additional_data":false},{"leaderboard":"/sota/timedial-on-big-bench","task":"Timedial","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"50.9"},"uses_additional_data":false},{"leaderboard":"/sota/triviaqa-on-big-bench","task":"TriviaQA","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=64)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"57.1"},"uses_additional_data":false},{"leaderboard":"/sota/us-foreign-policy-on-big-bench","task":"US Foreign Policy","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy ":"81.0"},"uses_additional_data":false},{"leaderboard":"/sota/understanding-fables-on-big-bench","task":"Understanding Fables","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy ":"39.6"},"uses_additional_data":false},{"leaderboard":"/sota/virology-on-big-bench","task":"Virology","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"47.0"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-big-bench","task":"Word Sense Disambiguation","dataset":"BIG-bench (Anachronisms)","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":2,"of":6,"metrics":{"Accuracy":"56.4"},"uses_additional_data":false},{"leaderboard":"/sota/world-religions-on-big-bench","task":"World Religions","dataset":"BIG-bench","model":"Gopher-280B (few-shot, k=5)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"84.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2112.11446","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}