{"id":"hal","name":"HAL (Holistic Agent Leaderboard)","maker":"Princeton University","url":"https://hal.cs.princeton.edu","summary":"A leaderboard and evaluation harness that compares AI agents across several benchmarks on accuracy and cost.","details":"Runs the same agents on benchmarks covering software engineering, web tasks and scientific reproduction, and reports cost alongside accuracy. It also publishes agent logs for analysis.","open_source":false,"hosted":false,"verified":"2026-11-15","category":"benchmarks","category_name":"Agent benchmarks","page":"https://modelmoot.com/tools/hal","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}