{"url":"/dataset/hrs-bench","name":"HRS-Bench","full_name":"Holistic, Reliable, and Scalable Benchmark","description_markdown":"**HRS-Bench** is a concrete evaluation benchmark for T2I models that is Holistic, Reliable, and Scalable. It measures 13 skills that can be categorized into five major categories: accuracy, robustness, generalization, fairness, and bias. In addition, HRS-Bench covers 50 scenarios, including fashion, animals, transportation, food, and clothes.\r\n\r\nSource: [HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models](https://arxiv.org/pdf/2304.05390v1.pdf)\r\n\r\nImage Source: [HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models](https://arxiv.org/pdf/2304.05390v1.pdf)","description_withheld":null,"homepage":"https://eslambakr.github.io/hrsbench.github.io/","introduced_date":"2023-04-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/hrs-bench-holistic-reliable-and-scalable","title":"HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","first_author":"Eslam Mohamed BAKR","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text-to-Image Generation","url":"/task/text-to-image-generation","datasets_with_task":"/datasets/task/text-to-image-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["HRS-Bench"],"data_loaders":[],"num_papers_in_archive":6,"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."}