Mahal Systems

Overview › Benchmark catalog

UNDERWRITE

Fits insurance and lending agents that must collect information before deciding. Borrow the imperfect simulated user and the pass^k reliability drop as a reported metric.

What it asks the agent to do

  • gather applicant details from a simulated user over several turns
  • look up underwriting guidelines through noisy tools
  • decide whether and how to underwrite an insurance policy

What to borrow from it

user simulatorgrading design

Caveats

Vendor benchmark with no public code or task data; leaderboard already shows top models above 90%.

Details

Workloadsfinance, customer support, tool calling
Interactionmulti turn simulated user
Environmentapi sandbox
End state checkedNo
Toolsunderwriting knowledge and policy lookup tools
Gradingprogrammatic check, pass^k
Size300
Datasynthetic
Personal datanone
Licenseunknown
Harnessnone
Statusactive

Links