6h ago

Harvey and Baseten's post-trained open-weight AI agents match closed-source frontier models on the Legal Agent Benchmark

— The evaluation used over 1,200 long-horizon tasks.

——0——
Original post
sarah guoSG#219@SARANORMOUSOPGabe PereyraGPGabe Pereyra|@GABEPEREYRA

http://x.com/i/article/2059666894781554691

10:31 AM · May 27, 2026 View on X
71552114969.0K

Cluster engagement

25 snapshots

Sentiment

Pos50%
Neg50%

Positive users praise teamwork and predict dominance for Harvey and Baseten's open-weight legal agents while negative users dismiss post-training reliability and bet against the company's survival.

7 comments with sentiment.