Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Multimodal & Grounded benchmark
A Benchmark for Visual Question Answering using World Knowledge. Every model the catalog carries a published A-OKVQA value for, ranked by that value.
A visual question answering benchmark whose questions cannot be answered from the image alone and require commonsense or world knowledge. One model in the ModelChoice catalog has a published value.
Each point is a model with a published A-OKVQA value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
1 model with a published A-OKVQA value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Multiple choice and direct answer |
|---|---|---|---|
| 1 | PMTernary Bonsai 2 27B | Prism ML | 86.8 |
Evidence key: Observed
Rows are ordered by the value A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
What the benchmark measures and how its value is published, from the source’s own record.
A-OKVQA (A Benchmark for Visual Question Answering using World Knowledge) is a multimodal & grounded benchmark published by A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge. A visual question answering benchmark whose questions cannot be answered from the image alone and require commonsense or world knowledge. Its evaluation set is described by the source as knowledge-grounded visual question answering. The source rates its difficulty as commonsense and world knowledge about images.
Each model's result is published by A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge as multiple choice and direct answer. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 1 model that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
All leaderboards · Multimodal & Grounded capability leaderboard