Harvey Open-Sources Legal Agent Benchmark Spanning 1,200 Tasks
baseten · x · 2026-07-30
Legal AI platform Harvey has launched Harvey Research and open-sourced the Legal Agent Benchmark. This benchmark is the largest test set for long-horizon legal work, covering 1,200 tasks across more than 24 practice areas. Additionally, Harvey collaborated with various partners to demonstrate how its product suite executes legal work end-to-end.
More from Apps
- OpenAI Announces Free Frontier AI Access for 100,000 Scientists Through 2027 — Polymarket · 2026-07-30
- Zero-Asset 3D Destruction Game Built Using Gauntlet Loop Prompt Style — mattshumer_ · 2026-07-30
- Developer Builds AI-Powered NYC Housing Match Tool — davidfromkansas · 2026-07-30
- HeyGen's Video Podcast Feels Like a Recorded Show, User Says — hey_abusiddik · 2026-07-30
- Pangram 4 Launches: Only 1 False Positive Per 24,000 Docs — The Decoder · 2026-07-30
- OpenAI Launches ChatGPT for Academic Researchers, Expanding to 100k by 2027 — OpenAI · 2026-07-30