Harvey unveils Tenet, a legal model post-trained on Kimi K3, boosting all-pass rates by 82%

agihouse_org · x · 2026-08-24

Harvey introduced Tenet, its first model post-trained for legal, built with Fireworks AI: a rank-64 LoRA on the Kimi K3 base, trained on 2k legal tasks over public legal data, synthetic data, and human expert data simulating long-horizon legal work, on a B300 cluster. Tenet improves the all-pass rate by 82% on LAB and 22% on LAB Contracts versus the base model, achieving SOTA on LAB Contracts and second place on LAB; gains generalize to agentic benchmarks like Apex Agents - Corporate Law, Redline Bench, and Professional Reasoning Bench. Former OpenAI exec Liam Fedus noted that Cursor, Cognition, and now Harvey are all building their own SOTA models on open-source bases, translating proprietary data into their own intelligence.

Original post →

More from Models

Models channel →