{"url":"/sota/common-sense-reasoning-on-record","task":{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","note":null},"dataset":{"name":"ReCoRD","url":"/dataset/record"},"category":"Natural Language Processing","categories":["Natural Language Processing","Reasoning"],"category_note":null,"description":"Common sense reasoning tasks are intended to require the model to go beyond pattern \nrecognition. Instead, the model should use \"common sense\" or world knowledge\nto make inferences.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["EM","F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"EM":null,"F1":"higher"}},"counts":{"rows":45,"rows_with_code":23,"rows_with_paper_page":34,"rows_dated":34,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Turing NLR v5 XXL 5.4B (fine-tuned)","metrics":{"EM":"95.9","F1":"96.4"},"uses_additional_data":false,"paper_date":"2022-12-04","paper":"/paper/toward-efficient-language-model-pretraining","paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"ST-MoE-32B 269B (fine-tuned)","metrics":{"EM":"95.1"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/designing-effective-sparse-expert-models","paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","code":"https://github.com/tensorflow/mesh","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":3,"model":"DeBERTa-1.5B","metrics":{"EM":"94.1","F1":"94.5"},"uses_additional_data":false,"paper_date":"2020-06-05","paper":"/paper/deberta-decoding-enhanced-bert-with","paper_url":"https://arxiv.org/abs/2006.03654v6","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","code":"https://github.com/huggingface/transformers","n_code_links":14,"syntology":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":3}},{"rank_in_archive_order":4,"model":"PaLM 540B (finetuned)","metrics":{"EM":"94.0","F1":"94.6"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"syntology":{"n_ran":30,"n_unverified":7,"n_samples":37,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Vega v2 6B (fine-tuned)","metrics":{"EM":"93.9","F1":"94.4"},"uses_additional_data":false,"paper_date":"2022-12-04","paper":"/paper/toward-efficient-language-model-pretraining","paper_url":"https://arxiv.org/abs/2212.01853v1","paper_title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"T5-XXL 11B (fine-tuned)","metrics":{"EM":"93.4"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":2,"n_unverified":29,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":7,"model":"GESA 500M","metrics":{"EM":"91.7","F1":"92.2"},"uses_additional_data":false,"paper_date":"2023-07-19","paper":"/paper/integrating-a-heterogeneous-graph-with-entity","paper_url":"https://arxiv.org/abs/2307.10443v3","paper_title":"Integrating a Heterogeneous Graph with Entity-aware Self-attention using Relative Position Labels for Reading Comprehension Model","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"LUKE-Graph","metrics":{"EM":"91.2","F1":"91.5"},"uses_additional_data":false,"paper_date":"2023-03-12","paper":"/paper/luke-graph-a-transformer-based-approach-with","paper_url":"https://arxiv.org/abs/2303.06675v1","paper_title":"LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"LUKE (single model)","metrics":{"EM":"90.640","F1":"91.209"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"LUKE 483M","metrics":{"EM":"90.6","F1":"91.2"},"uses_additional_data":false,"paper_date":"2020-10-02","paper":"/paper/luke-deep-contextualized-entity","paper_url":"https://arxiv.org/abs/2010.01057v1","paper_title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","code":"https://github.com/huggingface/transformers","n_code_links":9,"syntology":{"n_ran":3,"n_unverified":7,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"KELM (finetuning RoBERTa-large based single model)","metrics":{"EM":"89.1","F1":"89.6"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/kelm-knowledge-enhanced-pre-trained-language","paper_url":"https://arxiv.org/abs/2109.04223v2","paper_title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","code":"https://github.com/nlp-anonymous-happy/anonymous-kg-guided-nlp","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"ST-MoE-L 4.1B (fine-tuned)","metrics":{"EM":"88.9"},"uses_additional_data":false,"paper_date":"2022-02-17","paper":"/paper/designing-effective-sparse-expert-models","paper_url":"https://arxiv.org/abs/2202.08906v2","paper_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","code":"https://github.com/tensorflow/mesh","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":13,"model":"FLAN 137B (prompt-tuned)","metrics":{"EM":"85.1"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"XLNet + MTL + Verifier (ensemble)","metrics":{"EM":"83.090","F1":"83.737"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":15,"model":"GPT-3 Large 760M (0-shot)","metrics":{"EM":"82.1"},"uses_additional_data":false,"paper_date":"2020-05-28","paper":"/paper/language-models-are-few-shot-learners","paper_url":"https://arxiv.org/abs/2005.14165v4","paper_title":"Language Models are Few-Shot Learners","code":"https://github.com/ggml-org/llama.cpp","n_code_links":67,"syntology":{"n_ran":15,"n_unverified":50,"n_samples":65,"n_pointer_only_licence":4}},{"rank_in_archive_order":16,"model":"CSRLM (single model)","metrics":{"EM":"81.780","F1":"82.584"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":17,"model":"XLNet + Verifier","metrics":{"EM":"81.5","F1":"82.7"},"uses_additional_data":false,"paper_date":"2019-11-01","paper":"/paper/pingan-smart-health-and-sjtu-at-coin-shared","paper_url":"https://aclanthology.org/D19-6011","paper_title":"Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":18,"model":"XLNet + MTL + Verifier (single model)","metrics":{"EM":"81.460","F1":"82.664"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"Switch Transformer 9B","metrics":{"EM":"79.9"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"{SKG-NET} (single model)","metrics":{"EM":"79.480","F1":"80.038"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"KELM (finetuning BERT-large based single model)","metrics":{"EM":"76.2","F1":"76.7"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/kelm-knowledge-enhanced-pre-trained-language","paper_url":"https://arxiv.org/abs/2109.04223v2","paper_title":"KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs","code":"https://github.com/nlp-anonymous-happy/anonymous-kg-guided-nlp","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"sMLP – deterministic 9.4B (0-shot)","metrics":{"EM":"73.4"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":23,"model":"FLAN 137B (zero-shot)","metrics":{"EM":"72.5"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":24,"model":"Gshard 9B","metrics":{"EM":"72.4"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":25,"model":"SKG-BERT (single model)","metrics":{"EM":"72.240","F1":"72.778"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":26,"model":"KT-NET (single model)","metrics":{"EM":"71.600","F1":"73.620"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":27,"model":"DCReader+BERT (single model)","metrics":{"EM":"69.490","F1":"71.138"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"HASH Layers 10B (0-shot)","metrics":{"EM":"67.2"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"GraphBert (single)","metrics":{"EM":"60.800","F1":"62.986"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"Base Layers 10B (0-shot)","metrics":{"EM":"60.7"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"GraphBert-WordNet (single)","metrics":{"EM":"59.860","F1":"61.885"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":32,"model":"GraphBert-NELL (single)","metrics":{"EM":"59.410","F1":"61.515"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":33,"model":"BERT-Base (single model)","metrics":{"EM":"54.040","F1":"56.065"},"uses_additional_data":false,"paper_date":"2018-10-11","paper":"/paper/bert-pre-training-of-deep-bidirectional","paper_url":"https://arxiv.org/abs/1810.04805v2","paper_title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","code":"https://github.com/huggingface/transformers","n_code_links":534,"syntology":{"n_ran":204,"n_unverified":455,"n_samples":659,"n_pointer_only_licence":149}},{"rank_in_archive_order":34,"model":"DocQA + ELMo","metrics":{"EM":"45.4","F1":"46.7"},"uses_additional_data":false,"paper_date":"2018-10-30","paper":"/paper/record-bridging-the-gap-between-human-and","paper_url":"http://arxiv.org/abs/1810.12885v1","paper_title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":35,"model":"N-Grammer 343M","metrics":{"EM":"28.9","F1":"29.9"},"uses_additional_data":false,"paper_date":"2022-07-13","paper":"/paper/n-grammer-augmenting-transformers-with-latent-1","paper_url":"https://arxiv.org/abs/2207.06366v1","paper_title":"N-Grammer: Augmenting Transformers with latent n-grams","code":"https://github.com/tensorflow/lingvo","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":6,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":36,"model":"T5-11B","metrics":{"F1":"94.1"},"uses_additional_data":false,"paper_date":"2019-10-23","paper":"/paper/exploring-the-limits-of-transfer-learning","paper_url":"https://arxiv.org/abs/1910.10683v4","paper_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":2,"n_unverified":29,"n_samples":31,"n_pointer_only_licence":0}},{"rank_in_archive_order":37,"model":"PaLM 2-L (one-shot)","metrics":{"F1":"93.8"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"syntology":null},{"rank_in_archive_order":38,"model":"PaLM 2-M (one-shot)","metrics":{"F1":"92.4"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"PaLM 2-S (one-shot)","metrics":{"F1":"92.1"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"syntology":null},{"rank_in_archive_order":40,"model":"GPT-3 175B (one-shot)","metrics":{"F1":"90.2"},"uses_additional_data":false,"paper_date":"2022-05-24","paper":"/paper/large-language-models-are-zero-shot-reasoners","paper_url":"https://arxiv.org/abs/2205.11916v4","paper_title":"Large Language Models are Zero-Shot Reasoners","code":"https://github.com/kojima-takeshi188/zero_shot_cot","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":4,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":41,"model":"AlexaTM 20B","metrics":{"F1":"88.4"},"uses_additional_data":false,"paper_date":"2022-08-02","paper":"/paper/alexatm-20b-few-shot-learning-using-a-large","paper_url":"https://arxiv.org/abs/2208.01448v2","paper_title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","code":"https://github.com/amazon-science/alexa-teacher-models","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":42,"model":"Bloomberg GPT 50B (1-shot)","metrics":{"F1":"82.8"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"syntology":null},{"rank_in_archive_order":43,"model":"OPT 66B (1-shot)","metrics":{"F1":"82.5"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"syntology":null},{"rank_in_archive_order":44,"model":"BLOOM 176B (1-shot)","metrics":{"F1":"78"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"syntology":null},{"rank_in_archive_order":45,"model":"GPT-NeoX 20B (1-shot)","metrics":{"F1":"67.9"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":16,"rows_with_any_sample_ran":12,"distinct_papers_with_graph_line":12,"distinct_papers_with_any_sample_ran":9,"samples_over_distinct_papers":{"n_ran":265,"n_unverified":573,"n_samples":838,"n_pointer_only_licence":162,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":273,"n_unverified":608,"n_samples":881,"n_pointer_only_licence":167,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}