MM-BrowserComp
MM-BrowserComp evaluates multimodal agents on web browsing and information retrieval tasks, testing a model's ability to perceive, navigate, and extract information from real web environments.
Progress Over Time
Interactive timeline showing model performance evolution on MM-BrowserComp
State-of-the-art frontier
Open
Proprietary
MM-BrowserComp Leaderboard
1 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Xiaomi | — | 262K | $0.40 / $2.00 |
Notice missing or incorrect data?
FAQ
Common questions about MM-BrowserComp
MM-BrowserComp evaluates multimodal agents on web browsing and information retrieval tasks, testing a model's ability to perceive, navigate, and extract information from real web environments.
The MM-BrowserComp leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, MiMo-V2-Omni by Xiaomi leads with a score of 0.520. The average score across all models is 0.520.
The highest MM-BrowserComp score is 0.520, achieved by MiMo-V2-Omni from Xiaomi.
1 models have been evaluated on the MM-BrowserComp benchmark, with 0 verified results and 1 self-reported results.
MM-BrowserComp is categorized under agents and multimodal. The benchmark evaluates multimodal models.