multimodal benchmark
MM-Mind2Web
A multimodal web navigation benchmark comprising 2,000 open-ended tasks spanning 137 websites across 31 domains. Each task includes HTML documents paired with webpage screenshots, action sequences, and complex web interactions.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
MM-Mind2Web Ranking
Higher score ranks better on this benchmark.
| 01 | AM Nova ProAmazon | 63.7% | 100.0% | 3 | C | |
| 02 | AMNova LiteAmazon | 60.7% | 50.0% | 3 | C | |
| 03 | AC | 55.8% | 0.0% | 3 | C |
MM-Mind2Web Score Distribution
A closer view of the leading scores on this benchmark.
MM-Mind2Web Highlights
The leading models and scores on this benchmark.
What is MM-Mind2Web?
What MM-Mind2Web measures and how its scores work.
A multimodal web navigation benchmark comprising 2,000 open-ended tasks spanning 137 websites across 31 domains. Each task includes HTML documents paired with webpage screenshots, action sequences, and complex web interactions.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- MM-Mind2Web
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- mm-mind2web|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MM-Mind2Web.
Which model scores highest on MM-Mind2Web?
Nova Pro is currently ranked first with 63.7%.
What does MM-Mind2Web measure?
A multimodal web navigation benchmark comprising 2,000 open-ended tasks spanning 137 websites across 31 domains. Each task includes HTML documents paired with webpage screenshots, action sequences, and complex web interactions.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.