Datasets › WinoGAViL
WinoGAViL
This dataset is collected via the WinoGAViL game to collect challenging vision-and-language associations. Inspired by the popular card game Codenames, a “spymaster” gives a textual cue related to several visual candidates, and another player has to identify them.
We use the game to collect 3.5K instances, finding that they are intuitive for humans (>90% Jaccard index) but challenging for state-of-the-art AI models, where the best model (ViLT) achieves a score of 52%, succeeding mostly where the cue is visually salient.
Researchers are welcome to evaluate models on this dataset. A simple intended use is zero-shot prediction: run vision-and-language model, producing a score for the (cue,image) pair, and taking the K pairs with the highest scores.
A supervised setting is also possible, code for re-running the experiments is available in the github repository. https://github.com/WinoGAViL/WinoGAViL-experiments
Benchmarks archive 2025-07-28
All 2 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 | ||||
|---|---|---|---|---|---|---|
| Visual Reasoning | WinoGAViL | Humans Jaccard Index 90 | WinoGAViL: Gamified Association Benchmark to Challenge... | winogavil/winogavil-experiments | 8 | Compare |
| Common Sense Reasoning | WinoGAViL | ViLT Jaccard Index 52 | WinoGAViL: Gamified Association Benchmark to Challenge... | winogavil/winogavil-experiments | 1 | Compare |
Papers archive 2025-07-28
1 shown of 1 paper 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 5. 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 | |||
|---|---|---|---|---|
| WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models | 1 | 9 | 25 Jul 2022 | ran 1 of 2 samples (1 unverified) |
Dataset loaders archive 2025-07-28
3 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
- WinoGAViL
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