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 7, 2026
Published models3
Registry coverage3
MetricScore
EvidenceB
MM-Mind2Web leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AM Nova ProAmazon | 63.7% | 100.0% | 3 | C | |
| 2 | AMNova LiteAmazon | 60.7% | 50.0% | 3 | C | |
| 3 | AC | 55.8% | 0.0% | 3 | C |
Score distribution
Top published rows on the benchmark's original scale.
MM-Mind2Web highlights
The top published results on this benchmark's own scale.
What is MM-Mind2Web?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MM-Mind2Web
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- mm-mind2web|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.