multimodal benchmark
VQAv2 (test) Leaderboard
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 17, 2026
Models1
Model coverage1
MetricScore
EvidenceB
VQAv2 (test) Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score75.2% | Percentile100.0% | Participants1 | EvidenceC | Evaluated |
VQAv2 (test) Highlights
The leading models and scores on this benchmark.
The Top AI Models for VQAv2 (test)
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis vqav2 (test) AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ME
- Score
- 75.2%
- Speed
- Up to 168 tok/s via Together
Strengths
- Ranks #1 of 1 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures VQAv2 (test), not total model capability
Selection summary
Best AI Models for VQAv2 (test)
Llama 3.2 11B Instruct currently leads VQAv2 (test) with 75.2%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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
- multimodal
- 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.