multimodal benchmark
VisualWebBench
A multimodal benchmark designed to assess the capabilities of multimodal large language models (MLLMs) across web page understanding and grounding tasks. Comprises 7 tasks (captioning, webpage QA, heading OCR, element OCR, element grounding, action prediction, and action grounding) with 1.5K human-curated instances from 139 real websites across 87 sub-domains.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
VisualWebBench Ranking
Higher score ranks better on this benchmark.
| 01 | AM Nova ProAmazon | 79.7% | 100.0% | 2 | C | |
| 02 | AMNova LiteAmazon | 77.7% | 0.0% | 2 | C |
VisualWebBench Score Distribution
A closer view of the leading scores on this benchmark.
VisualWebBench Highlights
The leading models and scores on this benchmark.
What is VisualWebBench?
What VisualWebBench measures and how its scores work.
A multimodal benchmark designed to assess the capabilities of multimodal large language models (MLLMs) across web page understanding and grounding tasks. Comprises 7 tasks (captioning, webpage QA, heading OCR, element OCR, element grounding, action prediction, and action grounding) with 1.5K human-curated instances from 139 real websites across 87 sub-domains.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- VisualWebBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- visualwebbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about VisualWebBench.
Which model scores highest on VisualWebBench?
Nova Pro is currently ranked first with 79.7%.
What does VisualWebBench measure?
A multimodal benchmark designed to assess the capabilities of multimodal large language models (MLLMs) across web page understanding and grounding tasks. Comprises 7 tasks (captioning, webpage QA, heading OCR, element OCR, element grounding, action prediction, and action grounding) with 1.5K human-curated instances from 139 real websites across 87 sub-domains.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.