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.
Related event: Harvey's First In-House Legal Model Tenet Built on China's Kimi K3(2 posts)→
More from Models
- Opus 5 might be a very deep model or use looping, commentator speculates — scaling01 · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- Nvidia-backed post-training pushes Nemotron 3.5 VL past frontier on dermatology diagnosis — LoganGrasby · 2026-10-16
- Gemini 4 Argon scores 97.5% on ARC-AGI-3, second lab above 95% — patience_cave · 2026-10-16
- Microsoft MAI claims SOTA 3T-param in-house base models, post-training results coming — soldni · 2026-10-16
- Datadog's Scout 1.0: post-trained GLM-5.3 Flash matches frontier models for AI SRE at lower cost — Tim_Dettmers · 2026-10-16