{"url":"/sota/common-sense-reasoning-on-winogrande","task":{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","note":null},"dataset":{"name":"WinoGrande","url":"/dataset/winogrande"},"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":["Accuracy"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":77,"rows_with_code":60,"rows_with_paper_page":76,"rows_dated":76,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"ST-MoE-32B 269B (fine-tuned)","metrics":{"Accuracy":"96.1"},"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":2,"model":"Unicorn 11B (fine-tuned)","metrics":{"Accuracy":"91.3"},"uses_additional_data":false,"paper_date":"2021-03-24","paper":"/paper/unicorn-on-rainbow-a-universal-commonsense","paper_url":"https://arxiv.org/abs/2103.13009v1","paper_title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","code":"https://github.com/allenai/rainbow","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"CompassMTL 567M with Tailor","metrics":{"Accuracy":"90.5"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/task-compass-scaling-multi-task-pre-training","paper_url":"https://arxiv.org/abs/2210.06277v1","paper_title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","code":"https://github.com/cooelf/compassmtl","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CompassMTL 567M","metrics":{"Accuracy":"89.6"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/task-compass-scaling-multi-task-pre-training","paper_url":"https://arxiv.org/abs/2210.06277v1","paper_title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","code":"https://github.com/cooelf/compassmtl","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"UnifiedQA 11B (fine-tuned)","metrics":{"Accuracy":"89.4"},"uses_additional_data":false,"paper_date":"2020-05-02","paper":"/paper/unifiedqa-crossing-format-boundaries-with-a","paper_url":"https://arxiv.org/abs/2005.00700v3","paper_title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","code":"https://github.com/allenai/unifiedqa","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"Claude 3 Opus (5-shot)","metrics":{"Accuracy":"88.5"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","paper_url":"https://www.anthropic.com/news/claude-3-family","paper_title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"GPT-4 (5-shot)","metrics":{"Accuracy":"87.5"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/gpt-4-technical-report-1","paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","code":"https://github.com/openai/evals","n_code_links":11,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"ExDeBERTa 567M","metrics":{"Accuracy":"87"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/task-compass-scaling-multi-task-pre-training","paper_url":"https://arxiv.org/abs/2210.06277v1","paper_title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","code":"https://github.com/cooelf/compassmtl","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"LLaMA-2 13B + MixLoRA","metrics":{"Accuracy":"86.3"},"uses_additional_data":false,"paper_date":"2024-04-22","paper":"/paper/mixlora-enhancing-large-language-models-fine","paper_url":"https://arxiv.org/abs/2404.15159v3","paper_title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","code":"https://github.com/TUDB-Labs/MixLoRA","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"LLaMA3 8B+MoSLoRA","metrics":{"Accuracy":"85.8"},"uses_additional_data":false,"paper_date":"2024-06-16","paper":"/paper/mixture-of-subspaces-in-low-rank-adaptation","paper_url":"https://arxiv.org/abs/2406.11909v3","paper_title":"Mixture-of-Subspaces in Low-Rank Adaptation","code":"https://github.com/wutaiqiang/moslora","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":11,"model":"PaLM 2-L (1-shot)","metrics":{"Accuracy":"83.0"},"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":12,"model":"LLaMA-3 8B + MixLoRA","metrics":{"Accuracy":"82.1"},"uses_additional_data":false,"paper_date":"2024-04-22","paper":"/paper/mixlora-enhancing-large-language-models-fine","paper_url":"https://arxiv.org/abs/2404.15159v3","paper_title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","code":"https://github.com/TUDB-Labs/MixLoRA","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"ST-MoE-L 4.1B (fine-tuned)","metrics":{"Accuracy":"81.7"},"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":14,"model":"GPT-3.5 (5-shot)","metrics":{"Accuracy":"81.6"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/gpt-4-technical-report-1","paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","code":"https://github.com/openai/evals","n_code_links":11,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"PaLM 540B (0-shot)","metrics":{"Accuracy":"81.1"},"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":32,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"Camelidae-8×34B","metrics":{"Accuracy":"80.9"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/parameter-efficient-sparsity-crafting-from","paper_url":"https://arxiv.org/abs/2401.02731v4","paper_title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","code":"https://github.com/wuhy68/parameter-efficient-moe","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"PaLM 2-M (1-shot)","metrics":{"Accuracy":"79.2"},"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":18,"model":"RoBERTa-Winogrande 355M (fine-tuned)","metrics":{"Accuracy":"79.1"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"syntology":null},{"rank_in_archive_order":19,"model":"PaLM 2-S (1-shot)","metrics":{"Accuracy":"77.9"},"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":20,"model":"Mixtral 8x7B (0-shot)","metrics":{"Accuracy":"77.2"},"uses_additional_data":false,"paper_date":"2024-01-08","paper":"/paper/mixtral-of-experts","paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","code":"https://github.com/jingyaogong/minimind","n_code_links":6,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"PaLM 62B (0-shot)","metrics":{"Accuracy":"77.0"},"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":32,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"PaLM-cont 62B (0-shot)","metrics":{"Accuracy":"77.0"},"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":32,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"LLaMA 65B (0-shot)","metrics":{"Accuracy":"77.0"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":37,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":24,"model":"LLaMA-2 7B + MixLoRA","metrics":{"Accuracy":"76.8"},"uses_additional_data":false,"paper_date":"2024-04-22","paper":"/paper/mixlora-enhancing-large-language-models-fine","paper_url":"https://arxiv.org/abs/2404.15159v3","paper_title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","code":"https://github.com/TUDB-Labs/MixLoRA","n_code_links":2,"syntology":{"n_ran":6,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"LLaMA 33B (0-shot)","metrics":{"Accuracy":"76.0"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":37,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":26,"model":"Mistral 7B (0-shot)","metrics":{"Accuracy":"75.3"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/mistral-7b","paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","code":"https://github.com/mistralai/mistral-src","n_code_links":6,"syntology":{"n_ran":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":1}},{"rank_in_archive_order":27,"model":"Claude 3 Sonnet (5-shot)","metrics":{"Accuracy":"75.1"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","paper_url":"https://www.anthropic.com/news/claude-3-family","paper_title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"Chinchilla 70B (0-shot)","metrics":{"Accuracy":"74.9"},"uses_additional_data":false,"paper_date":"2022-03-29","paper":"/paper/training-compute-optimal-large-language","paper_url":"https://arxiv.org/abs/2203.15556v1","paper_title":"Training Compute-Optimal Large Language Models","code":"https://github.com/karpathy/llama2.c","n_code_links":2,"syntology":{"n_ran":8,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":4}},{"rank_in_archive_order":29,"model":"Claude 3 Haiku (5-shot)","metrics":{"Accuracy":"74.2"},"uses_additional_data":false,"paper_date":"2024-03-04","paper":"/paper/the-claude-3-model-family-opus-sonnet-haiku","paper_url":"https://www.anthropic.com/news/claude-3-family","paper_title":"The Claude 3 Model Family: Opus, Sonnet, Haiku","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"Mistral 7B (0-shot)","metrics":{"Accuracy":"74.2"},"uses_additional_data":false,"paper_date":"2024-01-08","paper":"/paper/mixtral-of-experts","paper_url":"https://arxiv.org/abs/2401.04088v1","paper_title":"Mixtral of Experts","code":"https://github.com/jingyaogong/minimind","n_code_links":6,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":31,"model":"phi-1.5-web 1.3B (zero-shot)","metrics":{"Accuracy":"74.0"},"uses_additional_data":false,"paper_date":"2023-09-11","paper":"/paper/textbooks-are-all-you-need-ii-phi-1-5","paper_url":"https://arxiv.org/abs/2309.05463v1","paper_title":"Textbooks Are All You Need II: phi-1.5 technical report","code":"https://github.com/knowlab/bi-weekly-paper-presentation","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"Unified QA 406M (fine-tuned)","metrics":{"Accuracy":"73.3"},"uses_additional_data":false,"paper_date":"2020-05-02","paper":"/paper/unifiedqa-crossing-format-boundaries-with-a","paper_url":"https://arxiv.org/abs/2005.00700v3","paper_title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","code":"https://github.com/allenai/unifiedqa","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":1}},{"rank_in_archive_order":33,"model":"LLaMA 13B (0-shot)","metrics":{"Accuracy":"73.0"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":37,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":34,"model":"FLAN 137B (few-shot, k=16)","metrics":{"Accuracy":"72.8"},"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":35,"model":"G-DAUG-Combo + RoBERTa-Large","metrics":{"Accuracy":"71.4"},"uses_additional_data":false,"paper_date":"2020-04-24","paper":"/paper/g-daug-generative-data-augmentation-for","paper_url":"https://arxiv.org/abs/2004.11546v3","paper_title":"Generative Data Augmentation for Commonsense Reasoning","code":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":4}},{"rank_in_archive_order":36,"model":"FLAN 137B (0-shot)","metrics":{"Accuracy":"71.2"},"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":37,"model":"RWKV v5 Eagle 7B","metrics":{"Accuracy":"70.8"},"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":38,"model":"Branch-Train-MiX 4x7B (sampling top-1 expert)","metrics":{"Accuracy":"70.6"},"uses_additional_data":false,"paper_date":"2024-03-12","paper":"/paper/branch-train-mix-mixing-expert-llms-into-a","paper_url":"https://arxiv.org/abs/2403.07816v1","paper_title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","code":"https://github.com/Leeroo-AI/mergoo","n_code_links":1,"syntology":null},{"rank_in_archive_order":39,"model":"GPT-3 175B (0-shot)","metrics":{"Accuracy":"70.2"},"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":41,"n_unverified":24,"n_samples":65,"n_pointer_only_licence":4}},{"rank_in_archive_order":40,"model":"Gopher 280B (0-shot)","metrics":{"Accuracy":"70.1"},"uses_additional_data":false,"paper_date":"2021-12-08","paper":"/paper/scaling-language-models-methods-analysis-1","paper_url":"https://arxiv.org/abs/2112.11446v2","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","code":"https://github.com/allenai/dolma","n_code_links":3,"syntology":null},{"rank_in_archive_order":41,"model":"LLaMA 7B (0-shot)","metrics":{"Accuracy":"70.1"},"uses_additional_data":false,"paper_date":"2023-02-27","paper":"/paper/llama-open-and-efficient-foundation-language-1","paper_url":"https://arxiv.org/abs/2302.13971v1","paper_title":"LLaMA: Open and Efficient Foundation Language Models","code":"https://github.com/huggingface/transformers","n_code_links":57,"syntology":{"n_ran":37,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":42,"model":"BLOOM 176B (1-shot)","metrics":{"Accuracy":"67"},"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":"Pythia 12B (5-shot)","metrics":{"Accuracy":"66.6"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/pythia-a-suite-for-analyzing-large-language","paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","code":"https://github.com/Lightning-AI/lit-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":44,"model":"OPT 66B (1-shot)","metrics":{"Accuracy":"66.1"},"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":"BERT-Winogrande 345M (fine-tuned)","metrics":{"Accuracy":"64.9"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"syntology":null},{"rank_in_archive_order":46,"model":"Bloomberg GPT (one-shot)","metrics":{"Accuracy":"64.1"},"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":47,"model":"Pythia 12B (0-shot)","metrics":{"Accuracy":"63.9"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/pythia-a-suite-for-analyzing-large-language","paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","code":"https://github.com/Lightning-AI/lit-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":48,"model":"RoE-3B","metrics":{"Accuracy":"61.60"},"uses_additional_data":false,"paper_date":"2023-02-07","paper":"/paper/exploring-the-benefits-of-training-expert","paper_url":"https://arxiv.org/abs/2302.03202v2","paper_title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","code":"https://github.com/joeljang/rlphf","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":49,"model":"Pythia 6.9B (0-shot)","metrics":{"Accuracy":"60.9"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/pythia-a-suite-for-analyzing-large-language","paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","code":"https://github.com/Lightning-AI/lit-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":50,"model":"GPT-NeoX (one-shot)","metrics":{"Accuracy":"60.6"},"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":51,"model":"FLAN-T5-Large 783M","metrics":{"Accuracy":"59.9"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"syntology":null},{"rank_in_archive_order":52,"model":"Pythia 2.8B (0-shot)","metrics":{"Accuracy":"59.4"},"uses_additional_data":false,"paper_date":"2023-04-03","paper":"/paper/pythia-a-suite-for-analyzing-large-language","paper_url":"https://arxiv.org/abs/2304.01373v2","paper_title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","code":"https://github.com/Lightning-AI/lit-gpt","n_code_links":4,"syntology":null},{"rank_in_archive_order":53,"model":"RoBERTa-DPR 355M (0-shot)","metrics":{"Accuracy":"58.9"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"syntology":null},{"rank_in_archive_order":54,"model":"ALBERT-xxlarge 235M","metrics":{"Accuracy":"58.7"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":55,"model":"Flipped-3B","metrics":{"Accuracy":"58.56"},"uses_additional_data":false,"paper_date":"2022-10-06","paper":"/paper/guess-the-instruction-making-language-models","paper_url":"https://arxiv.org/abs/2210.02969v4","paper_title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","code":"https://github.com/seonghyeonye/flipped-learning","n_code_links":1,"syntology":null},{"rank_in_archive_order":56,"model":"GPT-2-XL 1.5B","metrics":{"Accuracy":"58.3"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"syntology":null},{"rank_in_archive_order":57,"model":"T0-3B (CoT fine-tuned)","metrics":{"Accuracy":"57.5"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/the-cot-collection-improving-zero-shot-and","paper_url":"https://arxiv.org/abs/2305.14045v2","paper_title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","code":"https://github.com/kaistai/cot-collection","n_code_links":2,"syntology":null},{"rank_in_archive_order":58,"model":"GPT-3 Large 760M (0-shot)","metrics":{"Accuracy":"57.4"},"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":41,"n_unverified":24,"n_samples":65,"n_pointer_only_licence":4}},{"rank_in_archive_order":59,"model":"RoBERTa-base 125M","metrics":{"Accuracy":"56.3"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":60,"model":"LaMini-F-T5 783M","metrics":{"Accuracy":"56"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"syntology":null},{"rank_in_archive_order":61,"model":"LaMini-GPT 1.5B","metrics":{"Accuracy":"56"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"syntology":null},{"rank_in_archive_order":62,"model":"BERT-large 345M","metrics":{"Accuracy":"55.6"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":63,"model":"KiC-770M","metrics":{"Accuracy":"55.30"},"uses_additional_data":false,"paper_date":"2022-10-28","paper":"/paper/knowledge-in-context-towards-knowledgeable","paper_url":"https://arxiv.org/abs/2210.16433v3","paper_title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":64,"model":"T5-Large 738M","metrics":{"Accuracy":"55.2"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"syntology":null},{"rank_in_archive_order":65,"model":"LaMini-T5 738M","metrics":{"Accuracy":"54.9"},"uses_additional_data":false,"paper_date":"2023-04-27","paper":"/paper/lamini-lm-a-diverse-herd-of-distilled-models","paper_url":"https://arxiv.org/abs/2304.14402v3","paper_title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","code":"https://github.com/mbzuai-nlp/lamini-lm","n_code_links":1,"syntology":null},{"rank_in_archive_order":66,"model":"RoBERTa-large 355M","metrics":{"Accuracy":"54.9"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":67,"model":"sMLP – deterministic 9.4B (0-shot)","metrics":{"Accuracy":"54.3"},"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":68,"model":"Switch Transformer 9B (0-shot)","metrics":{"Accuracy":"53.4"},"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":69,"model":"BERT-base 110M","metrics":{"Accuracy":"53.1"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":70,"model":"ALBERT-base 11M","metrics":{"Accuracy":"52.8"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":71,"model":"BERT-large 345M (0-shot)","metrics":{"Accuracy":"51.9"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"syntology":null},{"rank_in_archive_order":72,"model":"HASH Layers 10B (0-shot)","metrics":{"Accuracy":"51.7"},"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":73,"model":"Gshard 9B (0-shot)","metrics":{"Accuracy":"51.1"},"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":74,"model":"Base Layers 10B (0-shot)","metrics":{"Accuracy":"51"},"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":75,"model":"BERT-DPR 345M (0-shot)","metrics":{"Accuracy":"51"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"syntology":null},{"rank_in_archive_order":76,"model":"Random baseline","metrics":{"Accuracy":"50"},"uses_additional_data":false,"paper_date":"2021-04-16","paper":"/paper/back-to-square-one-bias-detection-training","paper_url":"https://arxiv.org/abs/2104.08161v2","paper_title":"Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":77,"model":"RoBERTa-large 355M (0-shot)","metrics":{"Accuracy":"50"},"uses_additional_data":false,"paper_date":"2019-07-24","paper":"/paper/winogrande-an-adversarial-winograd-schema","paper_url":"https://arxiv.org/abs/1907.10641v2","paper_title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","code":"https://github.com/vered1986/self_talk","n_code_links":10,"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":["Accuracy"],"entries":[{"paper":"/paper/arxiv-2604-13556","paper_title":"YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference","arxiv_id":"2604.13556","model":"YOCO++","row_label":"YOCO++","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"55.48"},"date":"2026-04-15","month_from_arxiv_id":null,"where_in_paper":"Table 1, row “YOCO++”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1 : Zero-shot accuracy on commonsense reasoning tasks.","cells":[{"column":"Accuracy","cell_text":"55.48","column_header":"WinoGrande","value":55.48,"table_index_0based":0,"row":5,"col":3}],"code":"3 of 5 ran"}]},"syntology":{"read_at":"2026-09-25T09:33:49+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":28,"rows_with_any_sample_ran":26,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":14,"samples_over_distinct_papers":{"n_ran":165,"n_unverified":69,"n_samples":234,"n_pointer_only_licence":33,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":412,"n_unverified":180,"n_samples":592,"n_pointer_only_licence":56,"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"}}}