{"url":"/dataset/seed-bench","name":"SEED-Bench","full_name":null,"description_markdown":"**SEED-Bench** consists of 19K multiple choice questions with accurate human annotations (~6 larger than existing benchmarks), which spans 12 evaluation dimensions including the comprehension of both the image and video modality.","description_withheld":null,"homepage":"https://github.com/ailab-cvc/seed-bench","introduced_date":"2023-07-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/seed-bench-benchmarking-multimodal-llms-with","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","first_author":"Bohao Li","url":null},"license":{"name":"Apache License Version 2.0","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Understanding","url":"/task/video-understanding","datasets_with_task":"/datasets/task/video-understanding"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SEED-Bench"],"data_loaders":[],"num_papers_in_archive":137,"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."}