Benchmark RadarFreightBidBench
FreightBidBench is a public-calibrated, closed-loop benchmark for real-time truckload bid acceptance with explicit operational feasibility and economics, including pickup reach, appointment windows, hours-of-service, and yard delays. It provides two full-horizon hindsight ceilings for evaluation.
- Released
- 2026-07-08
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Offers a reproducible benchmark for a dynamic stochastic decision problem that lacked public options, enabling evaluation of bid acceptance policies under operational constraints.
Motivation
Online truckload bid acceptance is a closed-loop stochastic decision problem in which a carrier or broker must, in real time, accept or reject a tendered load subject to operational feasibility, fleet repositioning costs, and opportunity cost against future demand.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.