Harvey Post-Trains Legal Model, Cutting Inference Costs 50% While Beating Frontier Models

Legal AI firm Harvey partnered with Applied Compute to post-train GLM-5.2 for its high-frequency Review Table product, surpassing frontier models in answer and citation quality while cutting inference costs by 50%.

2026-08-15 ~ 2026-08-15 · 4 related posts

• Harvey and Applied Compute Post-Train Legal Model, Pushing Quality-Cost Frontier — ypatil125 · 2026-08-15
• Harvey Post-Trains GLM-5.2 with Applied Compute: 50% Cost Reduction, Better Quality — ypatil125 · 2026-08-15
• Harvey Trains Custom Model to Cut Costs and Boost Quality in Legal Review — ypatil125 · 2026-08-15
• Harvey and Applied Compute train legal-specific model with SOTA accuracy at fraction of cost — rhythmrg · 2026-08-15