{"url":"/dataset/mt-bench","name":"MT-Bench","full_name":null,"description_markdown":"This dataset contains 3.3K expert-level pairwise human preferences for model responses generated by 6 models in response to 80 MT-bench questions. The 6 models are GPT-4, GPT-3.5, Claud-v1, Vicuna-13B, Alpaca-13B, and LLaMA-13B. The annotators are mostly graduate students with expertise in the topic areas of each of the questions.","description_withheld":null,"homepage":"","introduced_date":"2023-06-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","first_author":"Lianmin Zheng","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Human Judgment Correlation","url":"/task/human-judgment-correlation","datasets_with_task":"/datasets/task/human-judgment-correlation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MT-Bench"],"data_loaders":[],"num_papers_in_archive":531,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-generation-on-mt-bench","task":"Text Generation","dataset_variant":"MT-Bench","rows":0,"metrics":["score"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}