Mahal Systems BrowserArena
Fits teams that want pairwise human preference on live browsing rather than fixed tasks. Borrow the step-level human feedback and the captcha / pop-up / URL failure taxonomy.
What it asks the agent to do
- complete a user-submitted task on the open web
- get past captchas and pop-up banners
- navigate directly to the right URL
What to borrow from it
taxonomygrading design
Caveats
Not reproducible (live web, human votes); no task count published; no code release found.
Details
| Workloads | web browsing, general assistant |
|---|---|
| Interaction | single turn |
| Environment | browser |
| End state checked | No |
| Tools | live web browsing |
| Grading | human |
| Size | Not published |
| Data | real public |
| Personal data | possible |
| License | CC-BY-4.0 |
| Harness | none |
| Status | active |