Post-Trained NVIDIA Nemotron Beats Claude Opus in Legal Agent Tasks

ctnzr · x · 2026-08-12

Harvey, in collaboration with Trajectory Labs, post-trained the NVIDIA Nemotron 3.5 Lightning model on the Legal Agent Bench (LAB), achieving remarkable results:

Trajectory Labs notes that continual learning relies on cheaper retraining loops. While large models might run this loop every few weeks, smaller models like Nemotron 3.5 Lightning can be fine-tuned nightly, per customer, or even per legal matter, bringing metered intelligence closer to reality.

Original post →

More from coding & agent

coding & agent channel →