{"url":"/sota/chatbot-on-alpacaeval","task":{"name":"Chatbot","url":"/task/chatbot","note":null},"dataset":{"name":"AlpacaEval","url":"/dataset/alpacaeval"},"category":"Natural Language Processing","categories":["Methodology","Natural Language Processing","Speech"],"category_note":null,"description":"**Chatbot** or conversational AI is a language model designed and implemented to have conversations with humans. \r\n\r\n\r\n<span class=\"description-source\">Source: [Open Data Chatbot ](https://arxiv.org/abs/1909.03653)</span>\r\n\r\n[Image source](https://arxiv.org/pdf/2006.16779v3.pdf)","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":["Average win rate"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Average win rate":null}},"counts":{"rows":1,"rows_with_code":1,"rows_with_paper_page":1,"rows_dated":1,"rows_using_additional_data":1},"rows":[{"rank_in_archive_order":1,"model":"Yi 34B Chat","metrics":{"Average win rate":"27.2"},"uses_additional_data":true,"paper_date":"2024-03-07","paper":"/paper/yi-open-foundation-models-by-01-ai","paper_url":"https://arxiv.org/abs/2403.04652v3","paper_title":"Yi: Open Foundation Models by 01.AI","code":"https://github.com/01-ai/yi","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":2,"n_unverified":6,"n_samples":8,"n_pointer_only_licence":0,"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"}}}