# A-OKVQA leaderboard

Multimodal & Grounded benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/multimodal-grounded-aokvqa

A Benchmark for Visual Question Answering using World Knowledge. Every model the catalog carries a published A-OKVQA value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Multiple choice and direct answer |
| Tasks | Knowledge-grounded visual question answering |
| Difficulty | Commonsense and world knowledge about images |
| Published by | [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://arxiv.org/abs/2206.01718) |

A visual question answering benchmark whose questions cannot be answered from the image alone and require commonsense or world knowledge.

## A-OKVQA ranking

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 | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Ternary Bonsai 2 27B](https://modelchoice.dev/models/ternary-bonsai-2-27b) | Prism ML | 86.8 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
