{"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/galactica-a-large-language-model-for-science-1","title":"Galactica: A Large Language Model for Science","arxiv_id":"2211.09085","date":"2022-11-16","proceeding":null,"authors":["Ross Taylor","Marcin Kardas","Guillem Cucurull","Thomas Scialom","Anthony Hartshorn","Elvis Saravia","Andrew Poulton","Viktor Kerkez","Robert Stojnic"],"abstract":"Information overload is a major obstacle to scientific progress. The explosive growth in scientific literature and data has made it ever harder to discover useful insights in a large mass of information. Today scientific knowledge is accessed through search engines, but they are unable to organize scientific knowledge alone. In this paper we introduce Galactica: a large language model that can store, combine and reason about scientific knowledge. We train on a large scientific corpus of papers, reference material, knowledge bases and many other sources. We outperform existing models on a range of scientific tasks. On technical knowledge probes such as LaTeX equations, Galactica outperforms the latest GPT-3 by 68.2% versus 49.0%. Galactica also performs well on reasoning, outperforming Chinchilla on mathematical MMLU by 41.3% to 35.7%, and PaLM 540B on MATH with a score of 20.4% versus 8.8%. It also sets a new state-of-the-art on downstream tasks such as PubMedQA and MedMCQA dev of 77.6% and 52.9%. And despite not being trained on a general corpus, Galactica outperforms BLOOM and OPT-175B on BIG-bench. We believe these results demonstrate the potential for language models as a new interface for science. We open source the model for the benefit of the scientific community.","url_abs":"https://arxiv.org/abs/2211.09085v1","url_pdf":"https://arxiv.org/pdf/2211.09085v1.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":"galactica-a-large-language-model-for-science-1","repo_url":"https://github.com/paperswithcode/galai","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"anachronisms","task_name":"Anachronisms"},{"task_slug":"bias-detection","task_name":"Bias Detection"},{"task_slug":"citation-prediction","task_name":"Citation Prediction"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"iupac-name-prediction","task_name":"IUPAC Name Prediction"},{"task_slug":"knowledge-probing","task_name":"Knowledge Probing"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"mmlu","task_name":"MMLU"},{"task_slug":"math","task_name":"Math"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"mathematical-reasoning","task_name":"Mathematical Reasoning"},{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"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":"protein-annotation","task_name":"Protein Annotation"},{"task_slug":"protein-function-prediction","task_name":"Protein Function Prediction"},{"task_slug":"protein-structure-prediction","task_name":"Protein Structure Prediction"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"stereotypical-bias-analysis","task_name":"Stereotypical Bias Analysis"},{"task_slug":"tdc-admet-benchmarking-group","task_name":"TDC ADMET Benchmarking Group"},{"task_slug":"word-sense-disambiguation","task_name":"Word Sense Disambiguation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bloom","method_name":"BLOOM"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"chinchilla","method_name":"Chinchilla"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"galactica","method_name":"Galactica"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"palm","method_name":"PaLM"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"galactica","name":"Galactica","full_name":"Galactica"}],"results":[{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"GAL 120B","rank_in_archive_order":8,"of":11,"metrics":{"ICAT Score":"65.6","LMS":"75","SS":"56.2"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"GPT-3 (text-davinci-002)","rank_in_archive_order":10,"of":11,"metrics":{"ICAT Score":"60.8","LMS":"77.6","SS":"60.8"},"uses_additional_data":false},{"leaderboard":"/sota/bias-detection-on-stereoset-1","task":"Bias Detection","dataset":"StereoSet","model":"OPT 175B","rank_in_archive_order":11,"of":11,"metrics":{"ICAT Score":"60","LMS":"74.8","SS":"59.9"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"GAL 120B (zero-shot)","rank_in_archive_order":20,"of":54,"metrics":{"Accuracy":"67.9"},"uses_additional_data":true},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"GPT-3 (zero-shot)","rank_in_archive_order":33,"of":54,"metrics":{"Accuracy":"51.4"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":50,"of":54,"metrics":{"Accuracy":"32.9"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"OPT (few-shot, k=5)","rank_in_archive_order":52,"of":54,"metrics":{"Accuracy":"31.1"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"GAL 120B (0-shot)","rank_in_archive_order":9,"of":47,"metrics":{"Accuracy":"83.8"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"GPT-3 (zero-shot)","rank_in_archive_order":37,"of":47,"metrics":{"Accuracy":"68.8"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"BLOOM (5-shot)","rank_in_archive_order":43,"of":47,"metrics":{"Accuracy":"40.7"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"OPT (5-shot)","rank_in_archive_order":45,"of":47,"metrics":{"Accuracy":"37.4"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Minerva 540B (5-shot) mCoT","rank_in_archive_order":83,"of":135,"metrics":{"Accuracy":"33.6","Parameters (Billions)":"540"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"GAL 120B (5-shot) mCoT","rank_in_archive_order":103,"of":135,"metrics":{"Accuracy":"20.4","Parameters (Billions)":"120"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"GAL 120B <work>","rank_in_archive_order":107,"of":135,"metrics":{"Accuracy":"16.6","Parameters (Billions)":"120"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"GAL 30B (5-shot) mCoT","rank_in_archive_order":112,"of":135,"metrics":{"Accuracy":"12.7","Parameters (Billions)":"30"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"GAL 30B <work>","rank_in_archive_order":114,"of":135,"metrics":{"Accuracy":"11.4","Parameters (Billions)":"30"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"PaLM 540B (5-shot) mCoT","rank_in_archive_order":118,"of":135,"metrics":{"Accuracy":"8.8","Parameters (Billions)":"540"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"GPT-3 175B (8-shot)","rank_in_archive_order":129,"of":135,"metrics":{"Accuracy":"5.2","Parameters (Billions)":"175"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"GAL 30B","rank_in_archive_order":16,"of":20,"metrics":{"ROC-AUC":"72.7"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"GAL 120B","rank_in_archive_order":17,"of":20,"metrics":{"ROC-AUC":"61.7"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"GAL 6.7B","rank_in_archive_order":18,"of":20,"metrics":{"ROC-AUC":"58.4"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"GAL 1.3B","rank_in_archive_order":19,"of":20,"metrics":{"ROC-AUC":"57.6"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"GAL 125M","rank_in_archive_order":20,"of":20,"metrics":{"ROC-AUC":"56.1"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"Uni-Mol","rank_in_archive_order":16,"of":29,"metrics":{"ROC-AUC":"72.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"GAL 120B","rank_in_archive_order":25,"of":29,"metrics":{"ROC-AUC":"66.1"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"GAL 1.3B","rank_in_archive_order":26,"of":29,"metrics":{"ROC-AUC":"60.4"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"GAL 30B","rank_in_archive_order":27,"of":29,"metrics":{"ROC-AUC":"59.6"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"GAL 6.7B","rank_in_archive_order":28,"of":29,"metrics":{"ROC-AUC":"53.5"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"GAL 125M","rank_in_archive_order":29,"of":29,"metrics":{"ROC-AUC":"39.3"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-dataset","task":"Molecular Property Prediction","dataset":"HIV dataset","model":"Uni-Mol","rank_in_archive_order":2,"of":11,"metrics":{"AUC":"0.808"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-dataset","task":"Molecular Property Prediction","dataset":"HIV dataset","model":"GAL 30B","rank_in_archive_order":7,"of":11,"metrics":{"AUC":"0.759"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-dataset","task":"Molecular Property Prediction","dataset":"HIV dataset","model":"GAL 120B","rank_in_archive_order":8,"of":11,"metrics":{"AUC":"0.745"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-dataset","task":"Molecular Property Prediction","dataset":"HIV dataset","model":"GAL 1.3B","rank_in_archive_order":9,"of":11,"metrics":{"AUC":"0.724"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-dataset","task":"Molecular Property Prediction","dataset":"HIV dataset","model":"GAL 6.7B","rank_in_archive_order":10,"of":11,"metrics":{"AUC":"0.722"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-hiv-dataset","task":"Molecular Property Prediction","dataset":"HIV dataset","model":"GAL 125M","rank_in_archive_order":11,"of":11,"metrics":{"AUC":"0.702"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-moleculenet","task":"Molecular Property Prediction","dataset":"MoleculeNet","model":"Uni-Mol","rank_in_archive_order":1,"of":5,"metrics":{"AUC":"0.77"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-moleculenet","task":"Molecular Property Prediction","dataset":"MoleculeNet","model":"GAL 30B","rank_in_archive_order":2,"of":5,"metrics":{"AUC":"0.69"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-moleculenet","task":"Molecular Property Prediction","dataset":"MoleculeNet","model":"GAL 6.7B","rank_in_archive_order":3,"of":5,"metrics":{"AUC":"0.64"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-moleculenet","task":"Molecular Property Prediction","dataset":"MoleculeNet","model":"GAL 1.3B","rank_in_archive_order":4,"of":5,"metrics":{"AUC":"0.619"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-moleculenet","task":"Molecular Property Prediction","dataset":"MoleculeNet","model":"GAL 125M","rank_in_archive_order":5,"of":5,"metrics":{"AUC":"0.581"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","task":"Molecular Property Prediction","dataset":"SIDER","model":"GAL 120B","rank_in_archive_order":13,"of":19,"metrics":{"ROC-AUC":"63.2"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","task":"Molecular Property Prediction","dataset":"SIDER","model":"GAL 30B","rank_in_archive_order":15,"of":19,"metrics":{"ROC-AUC":"61.3"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","task":"Molecular Property Prediction","dataset":"SIDER","model":"GAL 125M","rank_in_archive_order":17,"of":19,"metrics":{"ROC-AUC":"55.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","task":"Molecular Property Prediction","dataset":"SIDER","model":"GAL 6.7B","rank_in_archive_order":18,"of":19,"metrics":{"ROC-AUC":"55.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","task":"Molecular Property Prediction","dataset":"SIDER","model":"GAL 1.3B","rank_in_archive_order":19,"of":19,"metrics":{"ROC-AUC":"54.0"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"Uni-Mol","rank_in_archive_order":6,"of":20,"metrics":{"ROC-AUC":"79.6"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"GAL 120B","rank_in_archive_order":16,"of":20,"metrics":{"ROC-AUC":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"GAL 30B","rank_in_archive_order":17,"of":20,"metrics":{"ROC-AUC":"68.5"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"GAL 6.7B","rank_in_archive_order":18,"of":20,"metrics":{"ROC-AUC":"63.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"GAL 1.3B","rank_in_archive_order":19,"of":20,"metrics":{"ROC-AUC":"60.6"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"GAL 125M","rank_in_archive_order":20,"of":20,"metrics":{"ROC-AUC":"54.3"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","task":"Molecular Property Prediction","dataset":"clintox","model":"GAL 120B","rank_in_archive_order":10,"of":20,"metrics":{"Molecules (M)":"2","ROC-AUC":"82.6"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","task":"Molecular Property Prediction","dataset":"clintox","model":"GAL 30B","rank_in_archive_order":11,"of":20,"metrics":{"Molecules (M)":"2","ROC-AUC":"82.2"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","task":"Molecular Property Prediction","dataset":"clintox","model":"GAL 6.7B","rank_in_archive_order":14,"of":20,"metrics":{"Molecules (M)":"2","ROC-AUC":"78.4"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","task":"Molecular Property Prediction","dataset":"clintox","model":"GAL 1.3B","rank_in_archive_order":18,"of":20,"metrics":{"Molecules (M)":"2","ROC-AUC":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","task":"Molecular Property Prediction","dataset":"clintox","model":"GAL 125M","rank_in_archive_order":20,"of":20,"metrics":{"Molecules (M)":"2","ROC-AUC":"51.8"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"GAL 120B (zero-shot)","rank_in_archive_order":25,"of":44,"metrics":{"Average (%)":"52.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-3","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Abstract Algebra)","model":"GAL 30B (zero-shot)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"33.3"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-3","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Abstract Algebra)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"31"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-3","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Abstract Algebra)","model":"GAL 120B (zero-shot)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"27"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-3","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Abstract Algebra)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"25"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-3","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Abstract Algebra)","model":"OPT (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"21"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-9","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Astronomy)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"73.0"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-9","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Astronomy)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"65.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-9","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Astronomy)","model":"GAL 120B (zero-shot)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"65.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-9","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Astronomy)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"25.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-9","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Astronomy)","model":"OPT (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"23.0"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-11","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Biology)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy":"79.9"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-11","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Biology)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":5,"of":8,"metrics":{"Accuracy":"70.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-11","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Biology)","model":"GAL 120B (zero-shot)","rank_in_archive_order":6,"of":8,"metrics":{"Accuracy":"68.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-11","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Biology)","model":"OPT (few-shot, k=5)","rank_in_archive_order":7,"of":8,"metrics":{"Accuracy":"30.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-11","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Biology)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":8,"of":8,"metrics":{"Accuracy":"28.5"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-13","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Chemistry)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"51"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-13","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Chemistry)","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"46"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-13","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Chemistry)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"45"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-13","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Chemistry)","model":"OPT (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"30"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-13","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Chemistry)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"19"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-15","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Computer Science)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"51.0"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-15","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Computer Science)","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"49"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-15","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Computer Science)","model":"OPT (few-shot, k=5)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"17.0"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-15","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Computer Science)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"6.0"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-7","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Mathematics)","model":"GAL 120B (zero-shot)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"43"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-7","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Mathematics)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"37"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-7","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Mathematics)","model":"OPT (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"33"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-7","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Mathematics)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"32"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-7","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Mathematics)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"25"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-18","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Physics)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"46.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-18","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Physics)","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"42.2"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-18","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Physics)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"34.3"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-18","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Physics)","model":"OPT (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"21.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-18","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (College Physics)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"18.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-4","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Econometrics)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"43"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-4","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Econometrics)","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"42.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-4","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Econometrics)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"38.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-4","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Econometrics)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"23.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-4","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Econometrics)","model":"OPT (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"21"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-17","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Electrical Engineer)","model":"GAL 120B (zero-shot)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"62.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-17","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Electrical Engineer)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"62.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-17","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Electrical Engineer)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"60"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-17","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Electrical Engineer)","model":"OPT (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"36.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-17","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Electrical Engineer)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"32.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-10","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Elementary Mathematics)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-10","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Elementary Mathematics)","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"38.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-10","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Elementary Mathematics)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"33.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-10","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Elementary Mathematics)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"27.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-10","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Elementary Mathematics)","model":"OPT (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"25.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-2","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Formal Logic)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"35.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-2","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Formal Logic)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"33.3"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-2","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Formal Logic)","model":"GAL 120B (zero-shot)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"32.5"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-2","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Formal Logic)","model":"OPT (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"29.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-2","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Formal Logic)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"26.2"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-12","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Biology)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"80.3"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-12","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Biology)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"71.3"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-12","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Biology)","model":"GAL 120B (zero-shot)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"69.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-12","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Biology)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"29.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-12","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Biology)","model":"OPT (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"27.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-14","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Chemistry)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"58.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-14","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Chemistry)","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"47.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-14","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Chemistry)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"23.2"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-14","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Chemistry)","model":"OPT (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"21.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-5","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Computer Science)","model":"GAL 120B (zero-shot)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"70"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-5","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Computer Science)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"58"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-5","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Computer Science)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"54"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-5","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Computer Science)","model":"OPT (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"30"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-5","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Computer Science)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"25"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-16","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Mathematics)","model":"GAL 120B (zero-shot)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"32.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-16","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Mathematics)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"31.9"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-16","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Mathematics)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"27"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-16","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Mathematics)","model":"OPT (few-shot, k=5)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"24.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-16","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Mathematics)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"23.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-19","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Physics)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"36.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-19","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Physics)","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"33.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-19","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Physics)","model":"OPT (few-shot, k=5)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"29.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-19","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Physics)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"25.2"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-20","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Statistics)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"58.8"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-20","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Statistics)","model":"Gopher (few-shot, k=5)","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"50"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-20","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Statistics)","model":"OPT (few-shot, k=5)","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"43.5"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-20","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Statistics)","model":"GAL 120B (zero-shot)","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"41.2"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-20","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (High School Statistics)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"19.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-6","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Machine Learning)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"41.1"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-6","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Machine Learning)","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"38.4"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-6","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Machine Learning)","model":"OPT (few-shot, k=5)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"28.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-6","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Machine Learning)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"25"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-8","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Medical Genetics)","model":"GAL 30B (zero-shot)","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy":"70"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-8","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Medical Genetics)","model":"Chinchilla (few-shot, k=5)","rank_in_archive_order":5,"of":8,"metrics":{"Accuracy":"69"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-8","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Medical Genetics)","model":"GAL 120B (zero-shot)","rank_in_archive_order":6,"of":8,"metrics":{"Accuracy":"68"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-8","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Medical Genetics)","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":7,"of":8,"metrics":{"Accuracy":"36"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-8","task":"Multiple Choice Question Answering (MCQA)","dataset":"MMLU (Medical Genetics)","model":"OPT (few-shot, k=5)","rank_in_archive_order":8,"of":8,"metrics":{"Accuracy":"35"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-21","task":"Multiple Choice Question Answering (MCQA)","dataset":"MedMCQA","model":"GAL 120B (zero-shot)","rank_in_archive_order":16,"of":22,"metrics":{"Dev Set (Acc-%)":"0.529"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-21","task":"Multiple Choice Question Answering (MCQA)","dataset":"MedMCQA","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":20,"of":22,"metrics":{"Dev Set (Acc-%)":"0.325"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-choice-question-answering-mcqa-on-21","task":"Multiple Choice Question Answering (MCQA)","dataset":"MedMCQA","model":"OPT (few-shot, k=5)","rank_in_archive_order":21,"of":22,"metrics":{"Dev Set (Acc-%)":"0.296"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-caspsimseq","task":"Protein Function Prediction","dataset":"CASPSimSeq","model":"GAL 120B","rank_in_archive_order":1,"of":5,"metrics":{"ROUGE-L":"0.252"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-caspsimseq","task":"Protein Function Prediction","dataset":"CASPSimSeq","model":"GAL 30B","rank_in_archive_order":2,"of":5,"metrics":{"ROUGE-L":"0.137"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-caspsimseq","task":"Protein Function Prediction","dataset":"CASPSimSeq","model":"GAL 6.7B","rank_in_archive_order":3,"of":5,"metrics":{"ROUGE-L":"0.109"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-caspsimseq","task":"Protein Function Prediction","dataset":"CASPSimSeq","model":"GAL 1.3B","rank_in_archive_order":4,"of":5,"metrics":{"ROUGE-L":"0.069"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-caspsimseq","task":"Protein Function Prediction","dataset":"CASPSimSeq","model":"GAL 125M","rank_in_archive_order":5,"of":5,"metrics":{"ROUGE-L":"0.062"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-paenseq","task":"Protein Function Prediction","dataset":"PaenSeq","model":"GAL 120B","rank_in_archive_order":1,"of":5,"metrics":{"ROUGE-L":"0.272"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-paenseq","task":"Protein Function Prediction","dataset":"PaenSeq","model":"GAL 30B","rank_in_archive_order":2,"of":5,"metrics":{"ROUGE-L":"0.196"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-paenseq","task":"Protein Function Prediction","dataset":"PaenSeq","model":"GAL 6.7B","rank_in_archive_order":3,"of":5,"metrics":{"ROUGE-L":"0.137"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-paenseq","task":"Protein Function Prediction","dataset":"PaenSeq","model":"GAL 1.3B","rank_in_archive_order":4,"of":5,"metrics":{"ROUGE-L":"0.084"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-paenseq","task":"Protein Function Prediction","dataset":"PaenSeq","model":"GAL 125M","rank_in_archive_order":5,"of":5,"metrics":{"ROUGE-L":"0.073"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-uniprotseq","task":"Protein Function Prediction","dataset":"UniProtSeq","model":"GAL 120B","rank_in_archive_order":1,"of":5,"metrics":{"ROUGE-L":"0.252"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-uniprotseq","task":"Protein Function Prediction","dataset":"UniProtSeq","model":"GAL 30B","rank_in_archive_order":2,"of":5,"metrics":{"ROUGE-L":"0.186"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-uniprotseq","task":"Protein Function Prediction","dataset":"UniProtSeq","model":"GAL 6.7B","rank_in_archive_order":3,"of":5,"metrics":{"ROUGE-L":"0.111"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-uniprotseq","task":"Protein Function Prediction","dataset":"UniProtSeq","model":"GAL 1.3B","rank_in_archive_order":4,"of":5,"metrics":{"ROUGE-L":"0.079"},"uses_additional_data":false},{"leaderboard":"/sota/protein-function-prediction-on-uniprotseq","task":"Protein Function Prediction","dataset":"UniProtSeq","model":"GAL 125M","rank_in_archive_order":5,"of":5,"metrics":{"ROUGE-L":"0.061"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspseq","task":"Protein Structure Prediction","dataset":"CASPSeq","model":"GAL 120B","rank_in_archive_order":1,"of":5,"metrics":{"Validation perplexity":"17.26"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspseq","task":"Protein Structure Prediction","dataset":"CASPSeq","model":"GAL 30B","rank_in_archive_order":2,"of":5,"metrics":{"Validation perplexity":"17.27"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspseq","task":"Protein Structure Prediction","dataset":"CASPSeq","model":"GAL 6.7B","rank_in_archive_order":3,"of":5,"metrics":{"Validation perplexity":"17.29"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspseq","task":"Protein Structure Prediction","dataset":"CASPSeq","model":"GAL 1.3B","rank_in_archive_order":4,"of":5,"metrics":{"Validation perplexity":"17.58"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspseq","task":"Protein Structure Prediction","dataset":"CASPSeq","model":"GAL 125M","rank_in_archive_order":5,"of":5,"metrics":{"Validation perplexity":"20.62"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspsimseq","task":"Protein Structure Prediction","dataset":"CASPSimSeq","model":"GAL 120B","rank_in_archive_order":1,"of":5,"metrics":{"Validation perplexity":"12.77"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspsimseq","task":"Protein Structure Prediction","dataset":"CASPSimSeq","model":"GAL 30B","rank_in_archive_order":2,"of":5,"metrics":{"Validation perplexity":"15.42"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspsimseq","task":"Protein Structure Prediction","dataset":"CASPSimSeq","model":"GAL 6.7B","rank_in_archive_order":3,"of":5,"metrics":{"Validation perplexity":"16.35"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspsimseq","task":"Protein Structure Prediction","dataset":"CASPSimSeq","model":"GAL 1.3B","rank_in_archive_order":4,"of":5,"metrics":{"Validation perplexity":"17.04"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-caspsimseq","task":"Protein Structure Prediction","dataset":"CASPSimSeq","model":"GAL 125M","rank_in_archive_order":5,"of":5,"metrics":{"Validation perplexity":"19.18"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-paenseq","task":"Protein Structure Prediction","dataset":"PaenSeq","model":"GAL 120B","rank_in_archive_order":1,"of":5,"metrics":{"Validation perplexity":"3.14"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-paenseq","task":"Protein Structure Prediction","dataset":"PaenSeq","model":"GAL 30B","rank_in_archive_order":2,"of":5,"metrics":{"Validation perplexity":"4.28"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-paenseq","task":"Protein Structure Prediction","dataset":"PaenSeq","model":"GAL 6.7B","rank_in_archive_order":3,"of":5,"metrics":{"Validation perplexity":"7.76"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-paenseq","task":"Protein Structure Prediction","dataset":"PaenSeq","model":"GAL 1.3B","rank_in_archive_order":4,"of":5,"metrics":{"Validation perplexity":"12.53"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-paenseq","task":"Protein Structure Prediction","dataset":"PaenSeq","model":"GAL 125M","rank_in_archive_order":5,"of":5,"metrics":{"Validation perplexity":"16.35"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-uniprotseq","task":"Protein Structure Prediction","dataset":"UniProtSeq","model":"GAL 120B","rank_in_archive_order":1,"of":5,"metrics":{"Validation perplexity":"5.54"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-uniprotseq","task":"Protein Structure Prediction","dataset":"UniProtSeq","model":"GAL 30B","rank_in_archive_order":2,"of":5,"metrics":{"Validation perplexity":"8.23"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-uniprotseq","task":"Protein Structure Prediction","dataset":"UniProtSeq","model":"GAL 6.7B","rank_in_archive_order":3,"of":5,"metrics":{"Validation perplexity":"11.58"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-uniprotseq","task":"Protein Structure Prediction","dataset":"UniProtSeq","model":"GAL 1.3B","rank_in_archive_order":4,"of":5,"metrics":{"Validation perplexity":"15.82"},"uses_additional_data":false},{"leaderboard":"/sota/protein-structure-prediction-on-uniprotseq","task":"Protein Structure Prediction","dataset":"UniProtSeq","model":"GAL 125M","rank_in_archive_order":5,"of":5,"metrics":{"Validation perplexity":"19.05"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-bioasq","task":"Question Answering","dataset":"BioASQ","model":"GAL 120B (zero-shot)","rank_in_archive_order":2,"of":7,"metrics":{"Accuracy":"94.3"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-bioasq","task":"Question Answering","dataset":"BioASQ","model":"BLOOM (zero-shot)","rank_in_archive_order":4,"of":7,"metrics":{"Accuracy":"91.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-bioasq","task":"Question Answering","dataset":"BioASQ","model":"OPT (zero-shot)","rank_in_archive_order":7,"of":7,"metrics":{"Accuracy":"81.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-medqa-usmle","task":"Question Answering","dataset":"MedQA","model":"GAL 120B (zero-shot)","rank_in_archive_order":20,"of":27,"metrics":{"Accuracy":"44.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-medqa-usmle","task":"Question Answering","dataset":"MedQA","model":"BLOOM (few-shot, k=5)","rank_in_archive_order":26,"of":27,"metrics":{"Accuracy":"23.3"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-medqa-usmle","task":"Question Answering","dataset":"MedQA","model":"OPT (few-shot, k=5)","rank_in_archive_order":27,"of":27,"metrics":{"Accuracy":"22.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-pubmedqa","task":"Question Answering","dataset":"PubMedQA","model":"GAL 120B (zero-shot)","rank_in_archive_order":10,"of":30,"metrics":{"Accuracy":"77.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-pubmedqa","task":"Question Answering","dataset":"PubMedQA","model":"BLOOM (zero-shot)","rank_in_archive_order":20,"of":30,"metrics":{"Accuracy":"73.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-pubmedqa","task":"Question Answering","dataset":"PubMedQA","model":"OPT (zero-shot)","rank_in_archive_order":24,"of":30,"metrics":{"Accuracy":"70.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"GAL 120B","rank_in_archive_order":10,"of":33,"metrics":{"MC1":"0.26"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"GAL 30B","rank_in_archive_order":12,"of":33,"metrics":{"MC1":"0.24"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"OPT 175B","rank_in_archive_order":18,"of":33,"metrics":{"MC1":"0.21"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"GAL 125M","rank_in_archive_order":21,"of":33,"metrics":{"MC1":"0.19"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"GAL 1.3B","rank_in_archive_order":22,"of":33,"metrics":{"MC1":"0.19"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-truthfulqa","task":"Question Answering","dataset":"TruthfulQA","model":"GAL 6.7B","rank_in_archive_order":23,"of":33,"metrics":{"MC1":"0.19"},"uses_additional_data":false},{"leaderboard":"/sota/stereotypical-bias-analysis-on-crows-pairs","task":"Stereotypical Bias Analysis","dataset":"CrowS-Pairs","model":"GAL 120B","rank_in_archive_order":1,"of":4,"metrics":{"Age":"69","Disability":"66.7","Gender":"51.9","Nationality":"51.6","Overall":"60.5","Physical Appearance":"58.7","Race/Color":"59.9","Religion":"51.9","Sexual Orientation":"77.4","Socioeconomic status":"65.7"},"uses_additional_data":false},{"leaderboard":"/sota/tdc-admet-benchmarking-group-on-tdcommons","task":"TDC ADMET Benchmarking Group","dataset":"tdcommons","model":"Galactica-GAL-120B","rank_in_archive_order":8,"of":12,"metrics":{"TDC.BBB_Martins":"0.661"},"uses_additional_data":false},{"leaderboard":"/sota/tdc-admet-benchmarking-group-on-tdcommons","task":"TDC ADMET Benchmarking Group","dataset":"tdcommons","model":"Galactica-GAL-1.3B","rank_in_archive_order":9,"of":12,"metrics":{"TDC.BBB_Martins":"0.604"},"uses_additional_data":false},{"leaderboard":"/sota/tdc-admet-benchmarking-group-on-tdcommons","task":"TDC ADMET Benchmarking Group","dataset":"tdcommons","model":"Galactica-GAL-30B","rank_in_archive_order":10,"of":12,"metrics":{"TDC.BBB_Martins":"0.596"},"uses_additional_data":false},{"leaderboard":"/sota/tdc-admet-benchmarking-group-on-tdcommons","task":"TDC ADMET Benchmarking Group","dataset":"tdcommons","model":"Galactica-GAL-6.7B","rank_in_archive_order":11,"of":12,"metrics":{"TDC.BBB_Martins":"0.535"},"uses_additional_data":false},{"leaderboard":"/sota/tdc-admet-benchmarking-group-on-tdcommons","task":"TDC ADMET Benchmarking Group","dataset":"tdcommons","model":"Galactica-GAL-125M","rank_in_archive_order":12,"of":12,"metrics":{"TDC.BBB_Martins":"0.393"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-big-bench","task":"Word Sense Disambiguation","dataset":"BIG-bench (Anachronisms)","model":"OPT 175B","rank_in_archive_order":3,"of":6,"metrics":{"Accuracy":"49.1"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-big-bench","task":"Word Sense Disambiguation","dataset":"BIG-bench (Anachronisms)","model":"GAL 120B (few-shot, k=5)","rank_in_archive_order":4,"of":6,"metrics":{"Accuracy":"48.7"},"uses_additional_data":false},{"leaderboard":"/sota/word-sense-disambiguation-on-big-bench","task":"Word Sense Disambiguation","dataset":"BIG-bench (Anachronisms)","model":"GAL 30B (few-shot, k=5)","rank_in_archive_order":5,"of":6,"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":"BLOOM 176B","rank_in_archive_order":6,"of":6,"metrics":{"Accuracy":"1.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.09085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09085"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/paperswithcode/galai","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"779d2e3138d09f2d","entry":"escape_custom_split_sequence","repo":"paperswithcode/galai","repo_kind":"official","path":"galai/utils.py","file_url":"https://github.com/paperswithcode/galai/blob/HEAD/galai/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"779d2e3138d09f2d"}},{"code_sha256_prefix":"282223027b104a81","entry":"extract_references_from_text","repo":"paperswithcode/galai","repo_kind":"official","path":"galai/utils.py","file_url":"https://github.com/paperswithcode/galai/blob/HEAD/galai/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"282223027b104a81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}