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…
- Modality
- multimodal
- Categories
- multimodal, reasoning, frontend_development, agents
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 3
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Nova Lite | Amazon | 0.607 | 2024-11-20 | evidence |
| Nova Pro | Amazon | 0.637 | 2024-11-20 | evidence |
| Qwen3-Coder 480B A35B Instruct | Qwen | 0.558 | 2025-01-31 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.