{"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/sentence-completion-on-hellaswag","task":{"name":"Sentence Completion","url":"/task/sentence-completion","note":null},"dataset":{"name":"HellaSwag","url":"/dataset/hellaswag"},"category":"Natural Language Processing","categories":["Natural Language Processing"],"category_note":null,"description":null,"description_from":null,"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":89,"rows_with_code":71,"rows_with_paper_page":86,"rows_dated":86,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"CompassMTL 567M with Tailor","metrics":{"Accuracy":"96.1"},"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":2,"model":"CompassMTL 567M","metrics":{"Accuracy":"95.6"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/task-compass-scaling-multi-task-pre-training","paper_url":"https://arxiv.org/abs/2210.06277v1","paper_title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","code":"https://github.com/cooelf/compassmtl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"DeBERTa-Large 304M (classification-based)","metrics":{"Accuracy":"95.6"},"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":4,"model":"GPT-4 (10-shot)","metrics":{"Accuracy":"95.3"},"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,"official":{"repos":["openai/evals"],"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":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1,"sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"rank_in_archive_order":5,"model":"LLaMA3+MoSLoRA","metrics":{"Accuracy":"95.0"},"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":6,"model":"DeBERTa-Large 304M","metrics":{"Accuracy":"94.7"},"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":7,"model":"LLaMA-2 13B + MixLoRA","metrics":{"Accuracy":"94.7"},"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":"Unicorn 11B (fine-tuned)","metrics":{"Accuracy":"93.9"},"uses_additional_data":true,"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":9,"model":"LLaMA-3 8B + MixLoRA","metrics":{"Accuracy":"93.3"},"uses_additional_data":false,"paper_date":"2024-04-22","paper":"/paper/mixlora-enhancing-large-language-models-fine","paper_url":"https://arxiv.org/abs/2404.15159v3","paper_title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","code":"https://github.com/TUDB-Labs/MixLoRA","n_code_links":2,"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":10,"model":"LLaMA-2 7B + MixLoRA","metrics":{"Accuracy":"93.1"},"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,"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":11,"model":"DeBERTa++","metrics":{"Accuracy":"93"},"uses_additional_data":false,"paper_date":"2020-06-05","paper":"/paper/deberta-decoding-enhanced-bert-with","paper_url":"https://arxiv.org/abs/2006.03654v6","paper_title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","code":"https://github.com/huggingface/transformers","n_code_links":14,"official":{"repos":["microsoft/DeBERTa"],"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","named_in_paper","unlocated"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":3,"sample_list":"/paper/deberta-decoding-enhanced-bert-with#ran","syntology_url":"https://syntology.ai/paper/2006.03654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.03654"}}}},{"rank_in_archive_order":12,"model":"ELECTRA-Large 335M (fine-tuned on DiscoSense and HellaSwag)","metrics":{"Accuracy":"91.5"},"uses_additional_data":false,"paper_date":"2022-10-22","paper":"/paper/discosense-commonsense-reasoning-with","paper_url":"https://arxiv.org/abs/2210.12478v1","paper_title":"DiscoSense: Commonsense Reasoning with Discourse Connectives","code":"https://github.com/prajjwal1/discosense","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":13,"model":"DBRX Instruct 132B (10-shot)","metrics":{"Accuracy":"89"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"TheBloke/llama-2-70b-Guanaco-QLoRA-fp16 (10-shot)","metrics":{"Accuracy":"88.3"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":15,"model":"ALBERT-XXL 235M","metrics":{"Accuracy":"88"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"PaLM 2-L (1-shot)","metrics":{"Accuracy":"87.4"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/palm-2-technical-report-1","paper_url":"https://arxiv.org/abs/2305.10403v3","paper_title":"PaLM 2 Technical Report","code":"https://github.com/eternityyw/tram-benchmark","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"ELECTRA-Large 335M (fine-tuned on HellaSwag)","metrics":{"Accuracy":"86.9"},"uses_additional_data":false,"paper_date":"2022-10-22","paper":"/paper/discosense-commonsense-reasoning-with","paper_url":"https://arxiv.org/abs/2210.12478v1","paper_title":"DiscoSense: Commonsense Reasoning with Discourse Connectives","code":"https://github.com/prajjwal1/discosense","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"PaLM 2-M (1-shot)","metrics":{"Accuracy":"86.7"},"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":19,"model":"MUPPET Roberta Large","metrics":{"Accuracy":"86.4"},"uses_additional_data":false,"paper_date":"2021-01-26","paper":"/paper/muppet-massive-multi-task-representations","paper_url":"https://arxiv.org/abs/2101.11038v1","paper_title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","code":"https://huggingface.co/facebook/muppet-roberta-base","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"LLaMA 65B + CFG (0-shot)","metrics":{"Accuracy":"86.3"},"uses_additional_data":false,"paper_date":"2023-06-30","paper":"/paper/stay-on-topic-with-classifier-free-guidance","paper_url":"https://arxiv.org/abs/2306.17806v1","paper_title":"Stay on topic with Classifier-Free Guidance","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"Falcon-180B (0-shot)","metrics":{"Accuracy":"85.9"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/the-falcon-series-of-open-language-models","paper_url":"https://arxiv.org/abs/2311.16867v2","paper_title":"The Falcon Series of Open Language Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"PaLM 2-S (1-shot)","metrics":{"Accuracy":"85.6"},"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,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"GPT-3.5 (10-shot)","metrics":{"Accuracy":"85.5"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/gpt-4-technical-report-1","paper_url":"https://arxiv.org/abs/2303.08774v5","paper_title":"GPT-4 Technical Report","code":"https://github.com/openai/evals","n_code_links":11,"official":{"repos":["openai/evals"],"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":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1,"sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"rank_in_archive_order":24,"model":"RoBERTa-Large Ensemble","metrics":{"Accuracy":"85.5"},"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":25,"model":"LLaMA 30B + CFG (0-shot)","metrics":{"Accuracy":"85.3"},"uses_additional_data":false,"paper_date":"2023-06-30","paper":"/paper/stay-on-topic-with-classifier-free-guidance","paper_url":"https://arxiv.org/abs/2306.17806v1","paper_title":"Stay on topic with Classifier-Free Guidance","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"LLaMA 2 70B (0-shot)","metrics":{"Accuracy":"85.3"},"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":27,"model":"HyKAS+CSKG","metrics":{"Accuracy":"85.0"},"uses_additional_data":false,"paper_date":"2019-10-30","paper":"/paper/towards-generalizable-neuro-symbolic-systems","paper_url":"https://arxiv.org/abs/1910.14087v1","paper_title":"Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"LLaMA 65B (0-shot)","metrics":{"Accuracy":"84.2"},"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":29,"model":"PaLM-540B (Few-Shot)","metrics":{"Accuracy":"83.8"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"official":null,"syntology":{"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0,"sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"rank_in_archive_order":30,"model":"PaLM-540B (1-shot)","metrics":{"Accuracy":"83.6"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"official":null,"syntology":{"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0,"sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"rank_in_archive_order":31,"model":"ExDeBERTa 567M","metrics":{"Accuracy":"83.6"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/task-compass-scaling-multi-task-pre-training","paper_url":"https://arxiv.org/abs/2210.06277v1","paper_title":"Task Compass: Scaling Multi-task Pre-training with Task Prefix","code":"https://github.com/cooelf/compassmtl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"PaLM-540B (0-shot)","metrics":{"Accuracy":"83.4"},"uses_additional_data":false,"paper_date":"2022-04-05","paper":"/paper/palm-scaling-language-modeling-with-pathways-1","paper_url":"https://arxiv.org/abs/2204.02311v5","paper_title":"PaLM: Scaling Language Modeling with Pathways","code":"https://github.com/lucidrains/CoCa-pytorch","n_code_links":7,"official":null,"syntology":{"n_ran":32,"n_constructed":16,"n_ran_checked":24,"n_instrument":8,"n_unverified":5,"n_samples":37,"n_pointer_only_licence":0,"sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"rank_in_archive_order":33,"model":"LLaMA 2 34B (0-shot)","metrics":{"Accuracy":"83.3"},"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":34,"model":"Camelidae-8×34B (10-shot)","metrics":{"Accuracy":"83.2"},"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,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"LLaMA 33B (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":36,"model":"Falcon-40B (0-shot)","metrics":{"Accuracy":"82.7"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/the-falcon-series-of-open-language-models","paper_url":"https://arxiv.org/abs/2311.16867v2","paper_title":"The Falcon Series of Open Language Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"Megatron-Turing NLG 530B (Few-Shot)","metrics":{"Accuracy":"82.4"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/using-deepspeed-and-megatron-to-train","paper_url":"https://arxiv.org/abs/2201.11990v3","paper_title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","code":"https://github.com/microsoft/DeepSpeed","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"Qwen2idae-16x14B (10-shot)","metrics":{"Accuracy":"82.3"},"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":39,"model":"LLaMA 13B + CFG (0-shot)","metrics":{"Accuracy":"82.1"},"uses_additional_data":false,"paper_date":"2023-06-30","paper":"/paper/stay-on-topic-with-classifier-free-guidance","paper_url":"https://arxiv.org/abs/2306.17806v1","paper_title":"Stay on topic with Classifier-Free Guidance","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"RoBERTa-Large 355M","metrics":{"Accuracy":"81.7"},"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":41,"model":"Mistral 7B (0-shot)","metrics":{"Accuracy":"81.3"},"uses_additional_data":false,"paper_date":"2023-10-10","paper":"/paper/mistral-7b","paper_url":"https://arxiv.org/abs/2310.06825v1","paper_title":"Mistral 7B","code":"https://github.com/mistralai/mistral-src","n_code_links":6,"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":42,"model":"Chinchilla 70B (0-shot)","metrics":{"Accuracy":"80.8"},"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":43,"model":"LLaMA 2 13B (0-shot)","metrics":{"Accuracy":"80.7"},"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":44,"model":"Megatron-Turing NLG 530B (1-shot)","metrics":{"Accuracy":"80.2"},"uses_additional_data":false,"paper_date":"2022-01-28","paper":"/paper/using-deepspeed-and-megatron-to-train","paper_url":"https://arxiv.org/abs/2201.11990v3","paper_title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","code":"https://github.com/microsoft/DeepSpeed","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"GPT-3 175B (few-shot, k=32)","metrics":{"Accuracy":"79.3"},"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":46,"model":"Gopher 280B (0-shot)","metrics":{"Accuracy":"79.2"},"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":47,"model":"LLaMA 13B (0-shot)","metrics":{"Accuracy":"79.2"},"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":48,"model":"GPT-3 (0-shot)","metrics":{"Accuracy":"78.9"},"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":49,"model":"LLaMA 2 7B (0-shot)","metrics":{"Accuracy":"77.2"},"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":50,"model":"Falcon-7B (0-shot)","metrics":{"Accuracy":"76.3"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/the-falcon-series-of-open-language-models","paper_url":"https://arxiv.org/abs/2311.16867v2","paper_title":"The Falcon Series of Open Language Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"LLaMA 7B (0-shot)","metrics":{"Accuracy":"76.1"},"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":52,"model":"BlooombergGPT 50B (1-shot)","metrics":{"Accuracy":"73.9"},"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":53,"model":"OPT 66B (1-shot)","metrics":{"Accuracy":"73.5"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/bloomberggpt-a-large-language-model-for","paper_url":"https://arxiv.org/abs/2303.17564v3","paper_title":"BloombergGPT: A Large Language Model for Finance","code":"https://github.com/yangletliu/finlora","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"BLOOM 176B (1-shot)","metrics":{"Accuracy":"73.2"},"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":55,"model":"Sheared-LLaMA-2.7B (50B)","metrics":{"Accuracy":"70.8"},"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":56,"model":"GPT-NeoX 20B (1-shot)","metrics":{"Accuracy":"68.4"},"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":57,"model":"Open-LLaMA-3B-v2","metrics":{"Accuracy":"67.6"},"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":58,"model":"Mamba-2.8B","metrics":{"Accuracy":"66.1"},"uses_additional_data":false,"paper_date":"2023-12-01","paper":"/paper/mamba-linear-time-sequence-modeling-with","paper_url":"https://arxiv.org/abs/2312.00752v2","paper_title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","code":"https://github.com/state-spaces/mamba","n_code_links":35,"official":{"repos":["state-spaces/mamba","radarFudan/mamba"],"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":28,"n_constructed":7,"n_ran_checked":20,"n_instrument":8,"n_unverified":34,"n_samples":62,"n_pointer_only_licence":29,"sample_list":"/paper/mamba-linear-time-sequence-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2312.00752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00752"}}}},{"rank_in_archive_order":59,"model":"Sheared-LLaMA-1.3B (50B)","metrics":{"Accuracy":"60.7"},"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":60,"model":"FLAN 137B (3-shot)","metrics":{"Accuracy":"59.2"},"uses_additional_data":false,"paper_date":"2021-09-03","paper":"/paper/finetuned-language-models-are-zero-shot","paper_url":"https://arxiv.org/abs/2109.01652v5","paper_title":"Finetuned Language Models Are Zero-Shot Learners","code":"https://github.com/hiyouga/llama-efficient-tuning","n_code_links":8,"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":61,"model":"Mamba-1.4B","metrics":{"Accuracy":"59.1"},"uses_additional_data":false,"paper_date":"2023-12-01","paper":"/paper/mamba-linear-time-sequence-modeling-with","paper_url":"https://arxiv.org/abs/2312.00752v2","paper_title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","code":"https://github.com/state-spaces/mamba","n_code_links":35,"official":{"repos":["state-spaces/mamba","radarFudan/mamba"],"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":28,"n_constructed":7,"n_ran_checked":20,"n_instrument":8,"n_unverified":34,"n_samples":62,"n_pointer_only_licence":29,"sample_list":"/paper/mamba-linear-time-sequence-modeling-with#ran","syntology_url":"https://syntology.ai/paper/2312.00752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00752"}}}},{"rank_in_archive_order":62,"model":"FLAN 137B (0-shot)","metrics":{"Accuracy":"56.7"},"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":63,"model":"sMLP – deterministic 9.4B (0-shot)","metrics":{"Accuracy":"54.5"},"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":"Switch Transformer 9B","metrics":{"Accuracy":"52.5"},"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":"GPT-3 Large 760M (0-shot)","metrics":{"Accuracy":"51.0"},"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":66,"model":"GPT-2-XL 1.5B","metrics":{"Accuracy":"50.9"},"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":67,"model":"OPT-6.7B","metrics":{"Accuracy":"50.3"},"uses_additional_data":false,"paper_date":"2023-12-12","paper":"/paper/llm-in-a-flash-efficient-large-language-model","paper_url":"https://arxiv.org/abs/2312.11514v3","paper_title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":68,"model":"LLM in a Flash (OPT-6.7B with Predictor)","metrics":{"Accuracy":"49.8"},"uses_additional_data":false,"paper_date":"2023-12-12","paper":"/paper/llm-in-a-flash-efficient-large-language-model","paper_url":"https://arxiv.org/abs/2312.11514v3","paper_title":"LLM in a flash: Efficient Large Language Model Inference with Limited Memory","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"FLAN-T5-Large 783M","metrics":{"Accuracy":"48.7"},"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":70,"model":"LaMini-GPT 1.5B","metrics":{"Accuracy":"48.3"},"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":71,"model":"BERT-Large 340M","metrics":{"Accuracy":"47.3"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}},{"rank_in_archive_order":72,"model":"LaMini-F-T5 783M","metrics":{"Accuracy":"43.7"},"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":73,"model":"GPT-1 117M","metrics":{"Accuracy":"41.7"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}},{"rank_in_archive_order":74,"model":"Flipped-3B","metrics":{"Accuracy":"41.6"},"uses_additional_data":false,"paper_date":"2022-10-06","paper":"/paper/guess-the-instruction-making-language-models","paper_url":"https://arxiv.org/abs/2210.02969v4","paper_title":"Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners","code":"https://github.com/seonghyeonye/flipped-learning","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":75,"model":"T0-3B (CoT fine-tuned)","metrics":{"Accuracy":"41.1"},"uses_additional_data":false,"paper_date":"2023-05-23","paper":"/paper/the-cot-collection-improving-zero-shot-and","paper_url":"https://arxiv.org/abs/2305.14045v2","paper_title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","code":"https://github.com/kaistai/cot-collection","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"LaMini-T5 738M","metrics":{"Accuracy":"40.6"},"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":77,"model":"BERT-Base 110M","metrics":{"Accuracy":"40.5"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}},{"rank_in_archive_order":78,"model":"T5-Large 738M","metrics":{"Accuracy":"38.9"},"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":79,"model":"Gshard 9B","metrics":{"Accuracy":"38"},"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":80,"model":"LSTM + BERT-Base","metrics":{"Accuracy":"36.2"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}},{"rank_in_archive_order":81,"model":"RoE-3B","metrics":{"Accuracy":"34.6"},"uses_additional_data":false,"paper_date":"2023-02-07","paper":"/paper/exploring-the-benefits-of-training-expert","paper_url":"https://arxiv.org/abs/2302.03202v2","paper_title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","code":"https://github.com/joeljang/rlphf","n_code_links":2,"official":{"repos":["joeljang/elm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/exploring-the-benefits-of-training-expert#ran","syntology_url":"https://syntology.ai/paper/2302.03202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.03202"}}}},{"rank_in_archive_order":82,"model":"ESIM + ElMo","metrics":{"Accuracy":"33.3"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}},{"rank_in_archive_order":83,"model":"HASH Layers 10B (0-shot)","metrics":{"Accuracy":"33"},"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":84,"model":"LSTM + GloVe","metrics":{"Accuracy":"31.7"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}},{"rank_in_archive_order":85,"model":"fastText","metrics":{"Accuracy":"31.6"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}},{"rank_in_archive_order":86,"model":"LSTM + ElMo","metrics":{"Accuracy":"31.4"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}},{"rank_in_archive_order":87,"model":"Base Layers 10B (0-shot)","metrics":{"Accuracy":"30.2"},"uses_additional_data":false,"paper_date":"2022-03-14","paper":"/paper/efficient-language-modeling-with-sparse-all","paper_url":"https://arxiv.org/abs/2203.06850v3","paper_title":"Efficient Language Modeling with Sparse all-MLP","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"KiC-770M","metrics":{"Accuracy":"29.6"},"uses_additional_data":false,"paper_date":"2022-10-28","paper":"/paper/knowledge-in-context-towards-knowledgeable","paper_url":"https://arxiv.org/abs/2210.16433v3","paper_title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"Random chance baseline","metrics":{"Accuracy":"25"},"uses_additional_data":false,"paper_date":"2019-05-19","paper":"/paper/hellaswag-can-a-machine-really-finish-your","paper_url":"https://arxiv.org/abs/1905.07830v1","paper_title":"HellaSwag: Can a Machine Really Finish Your Sentence?","code":"https://github.com/facebookresearch/text_characterization_toolkit","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":4,"sample_list":"/paper/hellaswag-can-a-machine-really-finish-your#ran","syntology_url":"https://syntology.ai/paper/1905.07830","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.07830"}}}}],"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), 57 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 1,552 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 29 proposed a result; of those 29, 16 gave no cell that passed the extractor's own checks, 13 were rejected by the independent check, 0 await a verdict and 0 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":89,"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":1552,"candidates":57,"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":29,"no_cell_passed_checks":16,"rejected_by_independent_check":13,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; 29 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":29,"shown_on_page":29,"no_cell_split":{"no_cell_passed_checks_in_ledger":16,"rows_refused_by_rule":16,"rows_no_cell_passed_checks":0},"rows":[{"arxiv_id":"2609.25081","outcome":"rejected","reason":null},{"arxiv_id":"2609.13356","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2609.01024","outcome":"rejected","reason":null},{"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":"2608.02703","outcome":"refused_by_rule","reason":"the value is not on the scale of the leaderboard column's archive values"},{"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":"2606.26587","outcome":"rejected","reason":null},{"arxiv_id":"2606.18246","outcome":"rejected","reason":null},{"arxiv_id":"2606.13867","outcome":"rejected","reason":null},{"arxiv_id":"2606.01495","outcome":"rejected","reason":null},{"arxiv_id":"2606.01062","outcome":"rejected","reason":null},{"arxiv_id":"2605.29716","outcome":"refused_by_rule","reason":"the table does not name the leaderboard's dataset"},{"arxiv_id":"2605.26315","outcome":"rejected","reason":null},{"arxiv_id":"2605.17471","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2605.11726","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric; the row is an ablation variant, not the method itself"},{"arxiv_id":"2605.08636","outcome":"rejected","reason":null},{"arxiv_id":"2605.02404","outcome":"refused_by_rule","reason":"the row label the model quoted is not the row's label"},{"arxiv_id":"2604.15706","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2604.13556","outcome":"rejected","reason":null},{"arxiv_id":"2604.07658","outcome":"refused_by_rule","reason":"the row is an ablation variant, not the method itself"},{"arxiv_id":"2603.23985","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.10623","outcome":"refused_by_rule","reason":"the number the model quoted is not the number printed in the cell it pointed at"},{"arxiv_id":"2602.08064","outcome":"refused_by_rule","reason":"one configuration gave two values for one column"},{"arxiv_id":"2602.05367","outcome":"rejected","reason":null},{"arxiv_id":"2602.00942","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":"2512.23461","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"},{"arxiv_id":"2508.18672","outcome":"refused_by_rule","reason":"the table's column header does not name the leaderboard's metric"}]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"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":45,"rows_with_any_sample_ran":43,"rows_with_a_run_with_no_instrument_failure":42,"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":12,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":11,"rows_community_repositories_only":13,"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":18,"distinct_papers_with_any_sample_ran":17,"distinct_papers_with_a_run_with_no_instrument_failure":16,"samples_over_distinct_papers":{"n_ran":264,"n_constructed":53,"n_ran_checked":199,"n_instrument":65,"n_unverified":140,"n_samples":404,"n_pointer_only_licence":107,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":750,"n_constructed":151,"n_ran_checked":559,"n_instrument":191,"n_unverified":387,"n_samples":1137,"n_pointer_only_licence":279,"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":"7c4598b9ae549b2a18204348a830327a6eba5cdc9bff8ee87d750574c0019385","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}