Datasets › WHOOPS!
WHOOPS!
WHOOPS! Is a dataset and benchmark for visual commonsense. The dataset is comprised of purposefully commonsense-defying images created by designers using publicly-available image generation tools like Midjourney. It contains commonsense-defying image from a wide range of reasons, deviations from expected social norms and everyday knowledge.
Benchmarks archive 2025-07-28
All 4 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Explanation Generation | WHOOPS! | Ground-truth Caption -> GPT3 (Oracle) Human (%) 68 | Breaking Common Sense: WHOOPS! A Vision-and-Language... | — | 7 | Compare |
| Image-to-Text Retrieval | WHOOPS! | BLIP2 FlanT5-XXL (Text-only FT) Specificity 94 | Breaking Common Sense: WHOOPS! A Vision-and-Language... | — | 7 | Compare |
| Image Captioning | WHOOPS! | BLIP2 FlanT5-XXL (Fine-tuned) BLEU-4 42 | Breaking Common Sense: WHOOPS! A Vision-and-Language... | — | 6 | Compare |
| Visual Question Answering (VQA) | WHOOPS! | BLIP2 FlanT5-XXL (Fine-tuned) Exact Match 21 | Breaking Common Sense: WHOOPS! A Vision-and-Language... | — | 6 | Compare |
Papers archive 2025-07-28
2 shown of 2 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 14. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
| Date | Samples run Syntology | |||
|---|---|---|---|---|
| VLIS: Unimodal Language Models Guide Multimodal Language Generation | 1 | 2 | 15 Oct 2023 | not harvested |
| Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images | 0 | 24 | 13 Mar 2023 | not harvested |
Dataset loaders archive 2025-07-28
2 loaders as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- WHOOPS!
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections