Benchmark
VQAv2 (test) Benchmark
What is VQAv2 (test)?
VQA v2.0 (Visual Question Answering v2.0) is a balanced dataset designed to counter language priors in visual question answering. It consists of complementary…
- Released
- 2016-12-02
- Modality
- multimodal
- Evaluates
- multimodal, reasoning, image to text, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
VQAv2 (test) results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Llama 3.2 11B Instruct | Meta | 0.752 | 2024-09-25 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.