{"url":"/dataset/mixeval","name":"MixEval","full_name":null,"description_markdown":"MixEval is a ground-truth-based dynamic benchmark derived from off-the-shelf benchmark mixtures, which evaluates LLMs with a highly capable model ranking (i.e., 0.96 correlation with Chatbot Arena) while running locally and quickly (6% the time and cost of running MMLU), with its queries being stably and effortlessly updated every month to avoid contamination.","description_withheld":null,"homepage":"https://github.com/Psycoy/MixEval/","introduced_date":"2024-06-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/mixeval-deriving-wisdom-of-the-crowd-from-llm","title":"MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures","first_author":"Jinjie Ni","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["MixEval"],"data_loaders":[],"num_papers_in_archive":14,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"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."}