{"url":"/sota/common-sense-reasoning-on-arc-challenge","task":{"name":"Common Sense Reasoning","url":"/task/common-sense-reasoning","note":null},"dataset":{"name":"ARC (Challenge)","url":"/dataset/arc"},"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":54,"rows_with_code":41,"rows_with_paper_page":52,"rows_dated":52,"rows_using_additional_data":5},"rows":[{"rank_in_archive_order":1,"model":"GPT-4 (few-shot, k=25)","metrics":{"Accuracy":"96.4"},"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":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":2,"model":"PaLM 2 (few-shot, CoT, SC)","metrics":{"Accuracy":"95.1"},"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":3,"model":"Shivaay (4B, few-shot, k=8)","metrics":{"Accuracy":"91.04"},"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":4,"model":"StupidLLM","metrics":{"Accuracy":"91.03"},"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":5,"model":"Claude 2 (few-shot, k=5)","metrics":{"Accuracy":"91"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"Claude 1.3 (few-shot, k=5)","metrics":{"Accuracy":"90"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"PaLM 540B (Self Improvement, Self Consistency)","metrics":{"Accuracy":"89.8"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":8,"model":"PaLM 540B (Self Consistency)","metrics":{"Accuracy":"88.7"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"PaLM 540B (Self Improvement, CoT Prompting)","metrics":{"Accuracy":"88.3"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"PaLM 540B (Self Improvement, Standard-Prompting)","metrics":{"Accuracy":"87.2"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"PaLM 540B (Standard-Prompting)","metrics":{"Accuracy":"87.1"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"ST-MoE-32B 269B (fine-tuned)","metrics":{"Accuracy":"86.5"},"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":"Claude Instant 1.1 (few-shot, k=5)","metrics":{"Accuracy":"85.7"},"uses_additional_data":false,"paper_date":"2023-07-11","paper":"/paper/model-card-and-evaluations-for-claude-models","paper_url":"https://www-files.anthropic.com/production/images/Model-Card-Claude-2.pdf","paper_title":"Model Card and Evaluations for Claude Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"GPT-3.5 (few-shot, k=25)","metrics":{"Accuracy":"85.2"},"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":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"PaLM 540B (CoT Prompting)","metrics":{"Accuracy":"85.2"},"uses_additional_data":false,"paper_date":"2022-10-20","paper":"/paper/large-language-models-can-self-improve","paper_url":"https://arxiv.org/abs/2210.11610v2","paper_title":"Large Language Models Can Self-Improve","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"LLaMA 3 8B + MoSLoRA (fine-tuned)","metrics":{"Accuracy":"81.5"},"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":17,"model":"LLaMA-3 8B + MixLoRA","metrics":{"Accuracy":"79.9"},"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":18,"model":"LLaMA-2 13B + MixLoRA","metrics":{"Accuracy":"69.9"},"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":19,"model":"PaLM 2-L (1-shot)","metrics":{"Accuracy":"69.2"},"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":20,"model":"GAL 120B (zero-shot)","metrics":{"Accuracy":"67.9"},"uses_additional_data":true,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":21,"model":"Camelidae-8×34B","metrics":{"Accuracy":"65.2"},"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":22,"model":"PaLM 2-M (1-shot)","metrics":{"Accuracy":"64.9"},"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":23,"model":"FLAN 137B (few-shot, k=13)","metrics":{"Accuracy":"63.8"},"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":24,"model":"FLAN 137B (zero-shot)","metrics":{"Accuracy":"63.1"},"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":25,"model":"PaLM 2-S (1-shot)","metrics":{"Accuracy":"59.6"},"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":26,"model":"LLaMA-2 7B + MixLoRA","metrics":{"Accuracy":"58.1"},"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":27,"model":"LLaMA 33B (zero-shot)","metrics":{"Accuracy":"57.8"},"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":26,"n_unverified":32,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":28,"model":"ST-MoE-L 4.1B (fine-tuned)","metrics":{"Accuracy":"56.9"},"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":29,"model":"LLaMA 65B (zero-shot)","metrics":{"Accuracy":"56.0"},"uses_additional_data":true,"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":26,"n_unverified":32,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":30,"model":"Mistral 7B (0-shot)","metrics":{"Accuracy":"55.5"},"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":9,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":1}},{"rank_in_archive_order":31,"model":"GPT-3 175B (1 shot)","metrics":{"Accuracy":"53.2"},"uses_additional_data":true,"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":32,"model":"LLaMA 13B (zero-shot)","metrics":{"Accuracy":"52.7"},"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":26,"n_unverified":32,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":33,"model":"GPT-3 (zero-shot)","metrics":{"Accuracy":"51.4"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"GPT-3 175B (0-shot)","metrics":{"Accuracy":"51.4"},"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":15,"n_unverified":50,"n_samples":65,"n_pointer_only_licence":4}},{"rank_in_archive_order":35,"model":"BLOOM 176B (1-shot)","metrics":{"Accuracy":"50.85"},"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":36,"model":"GLaM 64B/64E (0 shot)","metrics":{"Accuracy":"50.3"},"uses_additional_data":true,"paper_date":"2021-12-13","paper":"/paper/glam-efficient-scaling-of-language-models","paper_url":"https://arxiv.org/abs/2112.06905v2","paper_title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":37,"model":"UL2 20B (chain-of-thought + self-consistency)","metrics":{"Accuracy":"49.5"},"uses_additional_data":false,"paper_date":"2022-05-10","paper":"/paper/unifying-language-learning-paradigms","paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":16,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"Bloomberg GPT 50B (1-shot)","metrics":{"Accuracy":"48.63"},"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":39,"model":"GLaM 64B/64E (1 shot)","metrics":{"Accuracy":"48.2"},"uses_additional_data":true,"paper_date":"2021-12-13","paper":"/paper/glam-efficient-scaling-of-language-models","paper_url":"https://arxiv.org/abs/2112.06905v2","paper_title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":40,"model":"LLaMA 7B (zero-shot)","metrics":{"Accuracy":"47.6"},"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":26,"n_unverified":32,"n_samples":58,"n_pointer_only_licence":4}},{"rank_in_archive_order":41,"model":"GPT-NeoX 20B (1-shot)","metrics":{"Accuracy":"45.39"},"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":42,"model":"phi-1.5-web 1.3B (zero-shot)","metrics":{"Accuracy":"44.9"},"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":43,"model":"OPT 66B (one-shot)","metrics":{"Accuracy":"44.54"},"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":"OPT-175B","metrics":{"Accuracy":"43.94"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":9}},{"rank_in_archive_order":45,"model":"UL2 20B (chain-of-thought)","metrics":{"Accuracy":"42.9"},"uses_additional_data":false,"paper_date":"2022-05-10","paper":"/paper/unifying-language-learning-paradigms","paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":16,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"SparseGPT (175B, 50% Sparsity)","metrics":{"Accuracy":"41.3"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":9}},{"rank_in_archive_order":47,"model":"SparseGPT (175B, 4:8 Sparsity)","metrics":{"Accuracy":"39.85"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":9}},{"rank_in_archive_order":48,"model":"SparseGPT (175B, 2:4 Sparsity)","metrics":{"Accuracy":"38.99"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":9}},{"rank_in_archive_order":49,"model":"Pythia 12B (5-shot)","metrics":{"Accuracy":"36.8"},"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":"BLOOM (few-shot, k=5)","metrics":{"Accuracy":"32.9"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":51,"model":"Pythia 12B (0-shot)","metrics":{"Accuracy":"31.8"},"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":52,"model":"OPT (few-shot, k=5)","metrics":{"Accuracy":"31.1"},"uses_additional_data":false,"paper_date":"2022-11-16","paper":"/paper/galactica-a-large-language-model-for-science-1","paper_url":"https://arxiv.org/abs/2211.09085v1","paper_title":"Galactica: A Large Language Model for Science","code":"https://github.com/paperswithcode/galai","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":53,"model":"UL2 20B (zero-shot)","metrics":{"Accuracy":"29.8"},"uses_additional_data":false,"paper_date":"2022-05-10","paper":"/paper/unifying-language-learning-paradigms","paper_url":"https://arxiv.org/abs/2205.05131v3","paper_title":"UL2: Unifying Language Learning Paradigms","code":"https://github.com/google-research/google-research","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":16,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":54,"model":"OPT-175B (50% Sparsity)","metrics":{"Accuracy":"25.6"},"uses_additional_data":false,"paper_date":"2023-01-02","paper":"/paper/massive-language-models-can-be-accurately","paper_url":"https://arxiv.org/abs/2301.00774v3","paper_title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","code":"https://github.com/nvidia/tensorrt-model-optimizer","n_code_links":6,"syntology":{"n_ran":2,"n_unverified":10,"n_samples":12,"n_pointer_only_licence":9}}],"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":29,"rows_with_any_sample_ran":20,"distinct_papers_with_graph_line":11,"distinct_papers_with_any_sample_ran":8,"samples_over_distinct_papers":{"n_ran":69,"n_unverified":123,"n_samples":192,"n_pointer_only_licence":30,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":189,"n_unverified":361,"n_samples":550,"n_pointer_only_licence":88,"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"}}}