multimodal benchmark
VisualWebBench Leaderboard
VisualWebBench is a multimodal benchmark for assessing multimodal large language models (MLLMs) on web page understanding and grounding tasks using 1.5K human-curated instances from 139 real websites across 87 sub-domains.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
VisualWebBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAM Nova ProAmazon | Score79.70% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelAMNova LiteAmazon | Score77.70% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
VisualWebBench Highlights
The leading models and scores on this benchmark.
VisualWebBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for VisualWebBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is VisualWebBench?
What VisualWebBench measures and how its scores work.
VisualWebBench comprises 7 tasks: captioning, webpage QA, heading OCR, element OCR, element grounding, action prediction, and action grounding.
It measures MLLM capabilities in web page understanding and grounding, with results reported as a Score ratio.
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
- overall
LLM Stats. 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 79.70%.
What are the top three models on VisualWebBench?
The current leaders are Nova Pro (79.70%) and Nova Lite (77.70%).
Which VisualWebBench model has the lowest official input price?
Nova Lite has the lowest matched official input price at $0.06 input / $0.24 output per 1M tokens.
Which models are fastest among VisualWebBench results?
No matched runtime record is currently available.
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.