image to text benchmark
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 image pairs where the same question yields different answers, forcing models to rely on visual understanding rather than language bias. The dataset contains 1,105,904 questions across 204,721 COCO images, requiring understanding of vision, language, and commonsense knowledge.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
VQAv2 (test) Ranking
Higher score ranks better on this benchmark.
| 01 | ME | 75.2% | 100.0% | 1 | C |
VQAv2 (test) Highlights
The leading models and scores on this benchmark.
What is VQAv2 (test)?
What VQAv2 (test) measures and how its scores work.
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 image pairs where the same question yields different answers, forcing models to rely on visual understanding rather than language bias. The dataset contains 1,105,904 questions across 204,721 COCO images, requiring understanding of vision, language, and commonsense knowledge.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- VQAv2 (test)
- Modality
- multimodal
- Primary category
- image to text
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- vqav2-(test)|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about VQAv2 (test).
Which model scores highest on VQAv2 (test)?
Llama 3.2 11B Instruct is currently ranked first with 75.2%.
What does VQAv2 (test) measure?
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 image pairs where the same question yields different answers, forcing models to rely on visual understanding rather than language bias. The dataset contains 1,105,904 questions across 204,721 COCO images, requiring understanding of vision, language, and commonsense knowledge.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.