{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/question-answering-on-piqa","task":{"name":"Question Answering","url":"/task/question-answering","note":null},"dataset":{"name":"PIQA","url":"/dataset/piqa"},"category":"Natural Language Processing","categories":["Miscellaneous","Natural Language Processing","Reasoning"],"category_note":null,"description":"Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include [SQuAD](/dataset/squad), [HotPotQA](/dataset/hotpotqa), [bAbI](/dataset/babi-1), [TriviaQA](/dataset/triviaqa), [WikiQA](/dataset/wikiqa), and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.\r\n\r\n( Image credit: [SQuAD](https://rajpurkar.github.io/mlx/qa-and-squad/) )","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; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher"}},"counts":{"rows":67,"rows_with_code":62,"rows_with_paper_page":67,"rows_dated":67,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Unicorn 11B (fine-tuned)","metrics":{"Accuracy":"90.1"},"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,"official":{"repos":["allenai/rainbow"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/unicorn-on-rainbow-a-universal-commonsense#ran","syntology_url":"https://syntology.ai/paper/2103.13009","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.13009"}}}},{"rank_in_archive_order":2,"model":"LLaMA3 8B+MoSLoRA","metrics":{"Accuracy":"89.7"},"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,"official":{"repos":["wutaiqiang/moslora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6,"sample_list":"/paper/mixture-of-subspaces-in-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2406.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11909"}}}},{"rank_in_archive_order":3,"model":"CompassMTL 567M with Tailor","metrics":{"Accuracy":"88.3"},"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,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"LLaMA-3 8B + MixLoRA","metrics":{"Accuracy":"87.6"},"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,"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}}}},{"rank_in_archive_order":5,"model":"DeBERTa-Large 304M","metrics":{"Accuracy":"87.4"},"uses_additional_data":false,"paper_date":"2022-10-29","paper":"/paper/two-is-better-than-many-binary-classification","paper_url":"https://arxiv.org/abs/2210.16495v1","paper_title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","code":"https://github.com/declare-lab/team","n_code_links":1,"official":{"repos":["declare-lab/team"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/two-is-better-than-many-binary-classification#ran","syntology_url":"https://syntology.ai/paper/2210.16495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16495"}}}},{"rank_in_archive_order":6,"model":"CompassMTL 567M","metrics":{"Accuracy":"87.3"},"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,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"LLaMA-2 13B + MixLoRA","metrics":{"Accuracy":"86.8"},"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,"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}}}},{"rank_in_archive_order":8,"model":"Shakti-LLM (2.5B)","metrics":{"Accuracy":"86.2"},"uses_additional_data":false,"paper_date":"2024-10-15","paper":"/paper/shakti-a-2-5-billion-parameter-small-language","paper_url":"https://arxiv.org/abs/2410.11331v1","paper_title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"DeBERTa-Large 304M (classification-based)","metrics":{"Accuracy":"85.9"},"uses_additional_data":false,"paper_date":"2022-10-29","paper":"/paper/two-is-better-than-many-binary-classification","paper_url":"https://arxiv.org/abs/2210.16495v1","paper_title":"Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering","code":"https://github.com/declare-lab/team","n_code_links":1,"official":{"repos":["declare-lab/team"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_samples":7,"n_pointer_only_licence":0,"sample_list":"/paper/two-is-better-than-many-binary-classification#ran","syntology_url":"https://syntology.ai/paper/2210.16495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16495"}}}},{"rank_in_archive_order":10,"model":"ExDeBERTa 567M","metrics":{"Accuracy":"85.5"},"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,"official":null,"syntology":null},{"rank_in_archive_order":11,"model":"UnifiedQA 3B","metrics":{"Accuracy":"85.3"},"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,"official":{"repos":["allenai/unifiedqa"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_samples":7,"n_pointer_only_licence":1,"sample_list":"/paper/unifiedqa-crossing-format-boundaries-with-a#ran","syntology_url":"https://syntology.ai/paper/2005.00700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.00700"}}}},{"rank_in_archive_order":12,"model":"PaLM 2-L (1-shot)","metrics":{"Accuracy":"85.0"},"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,"official":null,"syntology":null},{"rank_in_archive_order":13,"model":"Mixtral 8x7B (0-shot)","metrics":{"Accuracy":"83.6"},"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,"official":null,"syntology":{"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}}}},{"rank_in_archive_order":14,"model":"PaLM 2-M (1-shot)","metrics":{"Accuracy":"83.2"},"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,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"LLaMA-2 7B + MixLoRA","metrics":{"Accuracy":"83.2"},"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,"official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]},"syntology":{"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_samples":11,"n_pointer_only_licence":0,"sample_list":"/paper/mixlora-enhancing-large-language-models-fine#ran","syntology_url":"https://syntology.ai/paper/2404.15159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15159"}}}},{"rank_in_archive_order":16,"model":"Mistral 7B (0-shot)","metrics":{"Accuracy":"83.0"},"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,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":2,"sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"rank_in_archive_order":17,"model":"LLaMA 65B (0-shot)","metrics":{"Accuracy":"82.8"},"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,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":18,"model":"LLaMA 2 70B (0-shot)","metrics":{"Accuracy":"82.8"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","code":"https://github.com/facebookresearch/llama","n_code_links":19,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":33,"n_constructed":7,"n_ran_checked":20,"n_instrument":13,"n_unverified":19,"n_samples":52,"n_pointer_only_licence":20,"sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"rank_in_archive_order":19,"model":"Camelidae-8×34B","metrics":{"Accuracy":"82.7"},"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,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"LLaMA 33B (0-shot)","metrics":{"Accuracy":"82.3"},"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,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":21,"model":"PaLM 2-S (1-shot)","metrics":{"Accuracy":"82.2"},"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,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"Mistral 7B (0-shot)","metrics":{"Accuracy":"82.2"},"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,"official":null,"syntology":{"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0,"sample_list":"/paper/mixtral-of-experts#ran","syntology_url":"https://syntology.ai/paper/2401.04088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.04088"}}}},{"rank_in_archive_order":23,"model":"MT-NLG 530B (0-shot)","metrics":{"Accuracy":"82.0"},"uses_additional_data":false,"paper_date":"2019-09-17","paper":"/paper/megatron-lm-training-multi-billion-parameter","paper_url":"https://arxiv.org/abs/1909.08053v4","paper_title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","code":"https://github.com/NVIDIA/Megatron-LM","n_code_links":10,"official":{"repos":["NVIDIA/Megatron-LM"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":12,"n_constructed":2,"n_ran_checked":7,"n_instrument":5,"n_unverified":35,"n_samples":47,"n_pointer_only_licence":15,"sample_list":"/paper/megatron-lm-training-multi-billion-parameter#ran","syntology_url":"https://syntology.ai/paper/1909.08053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.08053"}}}},{"rank_in_archive_order":24,"model":"LLaMA 2 34B (0-shot)","metrics":{"Accuracy":"81.9"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","code":"https://github.com/facebookresearch/llama","n_code_links":19,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":33,"n_constructed":7,"n_ran_checked":20,"n_instrument":13,"n_unverified":19,"n_samples":52,"n_pointer_only_licence":20,"sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"rank_in_archive_order":25,"model":"Gopher 280B (0-shot)","metrics":{"Accuracy":"81.8"},"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,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"Chinchilla 70B (0-shot)","metrics":{"Accuracy":"81.8"},"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,"official":null,"syntology":{"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":3,"n_samples":11,"n_pointer_only_licence":4,"sample_list":"/paper/training-compute-optimal-large-language#ran","syntology_url":"https://syntology.ai/paper/2203.15556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15556"}}}},{"rank_in_archive_order":27,"model":"FLAN 137B (few-shot, k=10)","metrics":{"Accuracy":"81.7"},"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,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"rank_in_archive_order":28,"model":"OPT-175B","metrics":{"Accuracy":"81.07"},"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,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":29,"model":"GPT-3 175B (0-shot)","metrics":{"Accuracy":"81.0"},"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,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":45,"n_constructed":0,"n_ran_checked":37,"n_instrument":8,"n_unverified":20,"n_samples":65,"n_pointer_only_licence":7,"sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"rank_in_archive_order":30,"model":"SparseGPT 175B (50% Sparsity)","metrics":{"Accuracy":"80.63"},"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,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":31,"model":"FLAN 137B (0-shot)","metrics":{"Accuracy":"80.5"},"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,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"syntology":{"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"rank_in_archive_order":32,"model":"LLaMA 2 13B (0-shot)","metrics":{"Accuracy":"80.5"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","code":"https://github.com/facebookresearch/llama","n_code_links":19,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":33,"n_constructed":7,"n_ran_checked":20,"n_instrument":13,"n_unverified":19,"n_samples":52,"n_pointer_only_licence":20,"sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"rank_in_archive_order":33,"model":"LLaMA 13B (0-shot)","metrics":{"Accuracy":"80.1"},"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,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":34,"model":"LLaMA 7B (0-shot)","metrics":{"Accuracy":"79.8"},"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,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":37,"n_constructed":9,"n_ran_checked":25,"n_instrument":12,"n_unverified":21,"n_samples":58,"n_pointer_only_licence":4,"sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"rank_in_archive_order":35,"model":"SparseGPT 175B (4:8 Sparsity)","metrics":{"Accuracy":"79.54"},"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,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":36,"model":"SparseGPT 175B (2:4 Sparsity)","metrics":{"Accuracy":"79.54"},"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,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":37,"model":"RoBERTa-Large 355M","metrics":{"Accuracy":"79.4"},"uses_additional_data":false,"paper_date":"2019-07-26","paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","paper_url":"https://arxiv.org/abs/1907.11692v1","paper_title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","code":"https://github.com/huggingface/transformers","n_code_links":67,"official":{"repos":["pytorch/fairseq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":37,"n_constructed":11,"n_ran_checked":36,"n_instrument":1,"n_unverified":11,"n_samples":48,"n_pointer_only_licence":24,"sample_list":"/paper/roberta-a-robustly-optimized-bert-pretraining#ran","syntology_url":"https://syntology.ai/paper/1907.11692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11692"}}}},{"rank_in_archive_order":38,"model":"LLaMA 2 7B (0-shot)","metrics":{"Accuracy":"78.8"},"uses_additional_data":false,"paper_date":"2023-07-18","paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","paper_url":"https://arxiv.org/abs/2307.09288v2","paper_title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","code":"https://github.com/facebookresearch/llama","n_code_links":19,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":33,"n_constructed":7,"n_ran_checked":20,"n_instrument":13,"n_unverified":19,"n_samples":52,"n_pointer_only_licence":20,"sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"rank_in_archive_order":39,"model":"Bloomberg GPT 50B (1-shot)","metrics":{"Accuracy":"77.9"},"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,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"OPT 66B (1-shot)","metrics":{"Accuracy":"77.6"},"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,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"RoBERTa-large 355M (fine-tuned)","metrics":{"Accuracy":"77.1"},"uses_additional_data":false,"paper_date":"2019-11-26","paper":"/paper/piqa-reasoning-about-physical-commonsense-in","paper_url":"https://arxiv.org/abs/1911.11641v1","paper_title":"PIQA: Reasoning about Physical Commonsense in Natural Language","code":"https://github.com/vered1986/self_talk","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"phi-1.5-web (1.3B)","metrics":{"Accuracy":"77"},"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,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"BLOOM 176B (1-shot)","metrics":{"Accuracy":"77"},"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,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"Pythia 12B (5-shot)","metrics":{"Accuracy":"76.7"},"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,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"Open-LLaMA-3B-v2","metrics":{"Accuracy":"76.2"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/sheared-llama-accelerating-language-model-pre","paper_url":"https://arxiv.org/abs/2310.06694v2","paper_title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","code":"https://github.com/princeton-nlp/llm-shearing","n_code_links":2,"official":{"repos":["princeton-nlp/llm-shearing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/sheared-llama-accelerating-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2310.06694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06694"}}}},{"rank_in_archive_order":46,"model":"Pythia 12B (0-shot)","metrics":{"Accuracy":"76"},"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,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"Sheared-LLaMA-2.7B","metrics":{"Accuracy":"75.8"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/sheared-llama-accelerating-language-model-pre","paper_url":"https://arxiv.org/abs/2310.06694v2","paper_title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","code":"https://github.com/princeton-nlp/llm-shearing","n_code_links":2,"official":{"repos":["princeton-nlp/llm-shearing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/sheared-llama-accelerating-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2310.06694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06694"}}}},{"rank_in_archive_order":48,"model":"GPT-NeoX 20B (1-shot)","metrics":{"Accuracy":"75.8"},"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,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"Pythia 6.9B (0-shot)","metrics":{"Accuracy":"75.2"},"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,"official":null,"syntology":null},{"rank_in_archive_order":50,"model":"Sheared-LLaMA-1.3B","metrics":{"Accuracy":"73.4"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/sheared-llama-accelerating-language-model-pre","paper_url":"https://arxiv.org/abs/2310.06694v2","paper_title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","code":"https://github.com/princeton-nlp/llm-shearing","n_code_links":2,"official":{"repos":["princeton-nlp/llm-shearing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/sheared-llama-accelerating-language-model-pre#ran","syntology_url":"https://syntology.ai/paper/2310.06694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06694"}}}},{"rank_in_archive_order":51,"model":"sMLP - deterministic 9.4B (0-shot)","metrics":{"Accuracy":"73"},"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,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"GPT-3 Large 760M (0-shot)","metrics":{"Accuracy":"72.9"},"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,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":45,"n_constructed":0,"n_ran_checked":37,"n_instrument":8,"n_unverified":20,"n_samples":65,"n_pointer_only_licence":7,"sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"rank_in_archive_order":53,"model":"FLAN-T5-Large 783M","metrics":{"Accuracy":"72.2"},"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,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"LaMini-GPT 1.5B","metrics":{"Accuracy":"71.3"},"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,"official":null,"syntology":null},{"rank_in_archive_order":55,"model":"LaMini-F-T5 783M","metrics":{"Accuracy":"70.6"},"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,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"GPT-2-XL 1.5B","metrics":{"Accuracy":"70.5"},"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,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"Pythia 1B (5-shot)","metrics":{"Accuracy":"70.4"},"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,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"GPT-2-small 124M (fine-tuned)","metrics":{"Accuracy":"69.2"},"uses_additional_data":false,"paper_date":"2019-11-26","paper":"/paper/piqa-reasoning-about-physical-commonsense-in","paper_url":"https://arxiv.org/abs/1911.11641v1","paper_title":"PIQA: Reasoning about Physical Commonsense in Natural Language","code":"https://github.com/vered1986/self_talk","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"Gshard 9B","metrics":{"Accuracy":"68.1"},"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,"official":null,"syntology":null},{"rank_in_archive_order":60,"model":"LaMini-T5 738M","metrics":{"Accuracy":"67.2"},"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,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"BERT-large 340M (fine-tuned)","metrics":{"Accuracy":"66.8"},"uses_additional_data":false,"paper_date":"2019-11-26","paper":"/paper/piqa-reasoning-about-physical-commonsense-in","paper_url":"https://arxiv.org/abs/1911.11641v1","paper_title":"PIQA: Reasoning about Physical Commonsense in Natural Language","code":"https://github.com/vered1986/self_talk","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"BERT-Large 340M","metrics":{"Accuracy":"66.7"},"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,"official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"syntology":{"n_ran":300,"n_constructed":75,"n_ran_checked":234,"n_instrument":66,"n_unverified":359,"n_samples":659,"n_pointer_only_licence":164,"sample_list":"/paper/bert-pre-training-of-deep-bidirectional#ran","syntology_url":"https://syntology.ai/paper/1810.04805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.04805"}}}},{"rank_in_archive_order":63,"model":"Base Layers 10B (0-shot)","metrics":{"Accuracy":"63.8"},"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,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"HASH Layers 10B (0-shot)","metrics":{"Accuracy":"63.8"},"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,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"T5-Large 738M","metrics":{"Accuracy":"55.9"},"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,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"OPT-175B (50% Sparsity)","metrics":{"Accuracy":"54.73"},"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,"official":{"repos":["ist-daslab/sparsegpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/massive-language-models-can-be-accurately#ran","syntology_url":"https://syntology.ai/paper/2301.00774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.00774"}}}},{"rank_in_archive_order":67,"model":"Random chance baseline","metrics":{"Accuracy":"50"},"uses_additional_data":false,"paper_date":"2019-11-26","paper":"/paper/piqa-reasoning-about-physical-commonsense-in","paper_url":"https://arxiv.org/abs/1911.11641v1","paper_title":"PIQA: Reasoning about Physical Commonsense in Natural Language","code":"https://github.com/vered1986/self_talk","n_code_links":2,"official":null,"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,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 83 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,543 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 59 proposed a result; of those 59, 31 gave no cell that passed the extractor's own checks, 18 were rejected by the independent check, 1 awaits a verdict and 9 were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":67,"metric_columns":1,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1543,"candidates":83,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":59,"no_cell_passed_checks":31,"rejected_by_independent_check":18,"accepted_not_placed":0,"awaiting_verdict":1,"placed":9,"placed_entries_listed":9,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): 9 placed; 59 newer papers judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":59,"shown_on_page":59,"no_cell_split":{"no_cell_passed_checks_in_ledger":31,"rows_refused_by_rule":31,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.27233","outcome":"rejected","reason":null},{"arxiv_id":"2609.25058","outcome":"rejected","reason":null},{"arxiv_id":"2609.18131","outcome":"placed","reason":null},{"arxiv_id":"2609.15160","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2609.00791","outcome":"refused_by_rule","reason":"the quoted value appears more than once in the row"},{"arxiv_id":"2608.21308","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2608.15062","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2607.28166","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2607.01218","outcome":"rejected","reason":null},{"arxiv_id":"2606.26650","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2606.26587","outcome":"placed","reason":null},{"arxiv_id":"2606.23607","outcome":"rejected","reason":null},{"arxiv_id":"2606.18246","outcome":"rejected","reason":null},{"arxiv_id":"2606.13867","outcome":"rejected","reason":null},{"arxiv_id":"2606.06470","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2606.03938","outcome":"refused_by_rule","reason":"the model pointed at a header row"},{"arxiv_id":"2606.02559","outcome":"rejected","reason":null},{"arxiv_id":"2606.01495","outcome":"rejected","reason":null},{"arxiv_id":"2606.01062","outcome":"rejected","reason":null},{"arxiv_id":"2606.00494","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.31164","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2605.29843","outcome":"placed","reason":null},{"arxiv_id":"2605.24144","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.18855","outcome":"rejected","reason":null},{"arxiv_id":"2605.17849","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2605.17471","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.11396","outcome":"rejected","reason":null},{"arxiv_id":"2605.10655","outcome":"rejected","reason":null},{"arxiv_id":"2605.10129","outcome":"refused_by_rule","reason":"the model pointed at a header row; the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2605.08636","outcome":"rejected","reason":null},{"arxiv_id":"2605.05838","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.02404","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2604.13556","outcome":"placed","reason":null},{"arxiv_id":"2604.11841","outcome":"placed","reason":null},{"arxiv_id":"2604.07658","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2604.06291","outcome":"placed","reason":null},{"arxiv_id":"2604.01609","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"arxiv_id":"2603.26511","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2603.22300","outcome":"rejected","reason":null},{"arxiv_id":"2603.08185","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2603.08083","outcome":"placed","reason":null},{"arxiv_id":"2603.05878","outcome":"rejected","reason":null},{"arxiv_id":"2603.01376","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2602.10796","outcome":"rejected","reason":null},{"arxiv_id":"2602.08064","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.06694","outcome":"placed","reason":null},{"arxiv_id":"2602.05367","outcome":"placed","reason":null},{"arxiv_id":"2602.00942","outcome":"awaiting","reason":null},{"arxiv_id":"2601.21579","outcome":"rejected","reason":null},{"arxiv_id":"2601.20745","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2601.07892","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2511.04805","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2511.04063","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2510.20984","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2510.10467","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2510.03206","outcome":"rejected","reason":null},{"arxiv_id":"2510.00565","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2509.22299","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values; the quoted value appears more than once in the row"},{"arxiv_id":"2509.12019","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":["Accuracy"],"entries":[{"paper":"/paper/arxiv-2609-18131","paper_title":"Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing","arxiv_id":"2609.18131","model":"2.54 Colla-Q","row_label":"2.54 Colla-Q","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"80.5"},"date":"2026-09-16","month_from_arxiv_id":null,"where_in_paper":"Table 1, row “2.54 Colla-Q”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1: Zero-shot task performance (%) of the quantized Mixtral 8 × 7B on…","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"80.5","column_header":"PIQA","value":80.5,"table_index_0based":0,"row":7,"col":3}],"code":"repository linked, no samples harvested","samples_harvested":0,"sample_list":null,"syntology":{"syntology_url":"https://syntology.ai/paper/2609.18131","mcp":null}},{"paper":"/paper/arxiv-2606-26587","paper_title":"SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference","arxiv_id":"2606.26587","model":"Llama-3.1-8B SharQ","row_label":"Llama-3.1-8B SharQ","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"80.20"},"date":"2026-06-25","month_from_arxiv_id":null,"where_in_paper":"Table 1, row “Llama-3.1-8B SharQ”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1: Zero-shot and few-shot evaluation of SharQ across three LLMs. Accuracy…","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"80.20","column_header":"PIQA","value":80.2,"table_index_0based":0,"row":3,"col":5}],"code":"3 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","samples_harvested":3,"sample_list":"/paper/arxiv-2606-26587#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2606.26587","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2606.26587"}}}},{"paper":"/paper/arxiv-2605-29843","paper_title":"HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization","arxiv_id":"2605.29843","model":"4 HARP · Llama 2 7B","row_label":"4 HARP","configuration":"Llama 2 7B","configuration_in_model":true,"configuration_not_shown_because":null,"values":{"Accuracy":"78.3"},"date":"2026-05-28","month_from_arxiv_id":null,"where_in_paper":"Table 2, row “4 HARP”","table_label":"2","table_label_from":"the caption's own label","table_position_1based":2,"caption_head":"Table 2: Zero-shot accuracy ( acc , ↑ ) under QuIP# (RHT) vs. HARP on Llama 2…","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"78.3","column_header":"Llama 2 7B / PIQA","value":78.3,"table_index_0based":1,"row":8,"col":5}],"code":"9 harvested: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","samples_harvested":9,"sample_list":"/paper/arxiv-2605-29843#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2605.29843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2605.29843"}}}},{"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":"71.16"},"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.","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"71.16","column_header":"PIQA","value":71.16,"table_index_0based":0,"row":5,"col":6}],"code":"5 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","samples_harvested":5,"sample_list":"/paper/arxiv-2604-13556#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2604.13556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2604.13556"}}}},{"paper":"/paper/arxiv-2604-11841","paper_title":"Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions","arxiv_id":"2604.11841","model":"Llama-3-8B PERA ( r=32 )","row_label":"Llama-3-8B PERA ( r=32 )","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"89.83"},"date":"2026-04-12","month_from_arxiv_id":null,"where_in_paper":"Table 1, row “Llama-3-8B PERA ( r=32 )”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1: Accuracy(%) comparison of LLaMA model with various fine-tuned methods…","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"89.83","column_header":"PIQA","value":89.83,"table_index_0based":0,"row":19,"col":4}],"code":"18 harvested: 15 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified","samples_harvested":18,"sample_list":"/paper/arxiv-2604-11841#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2604.11841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2604.11841"}}}},{"paper":"/paper/arxiv-2604-06291","paper_title":"TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models","arxiv_id":"2604.06291","model":"Qwen2.5-7B TalkLoRA ( r=16 )","row_label":"Qwen2.5-7B TalkLoRA ( r=16 )","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"90.9"},"date":"2026-04-07","month_from_arxiv_id":null,"where_in_paper":"Table 1, row “Qwen2.5-7B TalkLoRA ( r=16 )”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1: Accuracy(%) comparison of various methods fine-tuning Qwen2.5-7B,…","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"90.9","column_header":"PIQA","value":90.9,"table_index_0based":0,"row":4,"col":4}],"code":"2 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","samples_harvested":2,"sample_list":"/paper/arxiv-2604-06291#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2604.06291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2604.06291"}}}},{"paper":"/paper/arxiv-2603-08083","paper_title":"High-Fidelity Pruning for Large Language Models","arxiv_id":"2603.08083","model":"20% HFPrune (Ours)","row_label":"20% HFPrune (Ours)","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"77.3"},"date":"2026-03-09","month_from_arxiv_id":null,"where_in_paper":"Table 1, row “20% HFPrune (Ours)”","table_label":"1","table_label_from":"the caption's own label","table_position_1based":1,"caption_head":"Table 1: Zero-shot performance on LLaMA-2-7B, which are finetuned on the LaMini…","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"77.3","column_header":"PIQA","value":77.3,"table_index_0based":0,"row":6,"col":7}],"code":"held, no recorded run","samples_harvested":1,"sample_list":"/paper/arxiv-2603-08083#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2603.08083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2603.08083"}}}},{"paper":"/paper/arxiv-2602-06694","paper_title":"NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models","arxiv_id":"2602.06694","model":"Q3-8","row_label":"Q3-8","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"63.32"},"date":"2026-02-06","month_from_arxiv_id":null,"where_in_paper":"Table 3, row “Q3-8”","table_label":"3","table_label_from":"the caption's own label","table_position_1based":3,"caption_head":"Table 3 : Zero-shot accuracy comparison on commonsense reasoning tasks using…","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"63.32","column_header":"PIQA","value":63.32,"table_index_0based":2,"row":14,"col":8}],"code":"5 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","samples_harvested":5,"sample_list":"/paper/arxiv-2602-06694#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2602.06694","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2602.06694"}}}},{"paper":"/paper/arxiv-2602-05367","paper_title":"RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs","arxiv_id":"2602.05367","model":"Gemma3-12B RaBiT (Ours)","row_label":"Gemma3-12B RaBiT (Ours)","configuration":null,"configuration_in_model":false,"configuration_not_shown_because":null,"values":{"Accuracy":"78.95"},"date":"2026-02-05","month_from_arxiv_id":null,"where_in_paper":"Table 10, row “Gemma3-12B RaBiT (Ours)”","table_label":"10","table_label_from":"the caption's own label","table_position_1based":10,"caption_head":"Table 10 : Detailed Zero-Shot Reasoning Accuracy on Gemma Models (%).…","caption_on_page":"shown","cells":[{"column":"Accuracy","cell_text":"78.95","column_header":"PIQA \\uparrow","value":78.95,"table_index_0based":9,"row":12,"col":6}],"code":"6 harvested: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","samples_harvested":6,"sample_list":"/paper/arxiv-2602-05367#ran","syntology":{"syntology_url":"https://syntology.ai/paper/2602.05367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2602.05367"}}}}]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran 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).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":35,"rows_with_any_sample_ran":33,"rows_with_a_run_with_no_instrument_failure":33,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":32,"rows_whose_official_repository_has_a_sample_that_ran":17,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":12,"rows_community_repositories_only":8,"rows_runs_from_other_or_unrecorded_repositories":5,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":17,"distinct_papers_with_any_sample_ran":16,"distinct_papers_with_a_run_with_no_instrument_failure":16,"samples_over_distinct_papers":{"n_ran":518,"n_constructed":115,"n_ran_checked":400,"n_instrument":118,"n_unverified":490,"n_samples":1008,"n_pointer_only_licence":256,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":834,"n_constructed":168,"n_ran_checked":615,"n_instrument":219,"n_unverified":658,"n_samples":1492,"n_pointer_only_licence":371,"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"}},"record_sha256":"e9785e6caea8b4a58fe5b5ff31225f76570109187a11284c33400fe23acffce9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}