Harvey, Trajectory Post-Train Nvidia Nemotron 3 Ultra for Legal, Raise All-Pass Rate to 5.8%
Harvey and Trajectory Labs said they post-trained Nvidia Nemotron 3 Ultra for legal work on Harvey’s Legal Agent Benchmark less than 24 hours after the model launched. Harvey said the open-weight model’s all-pass rate rose to 5.8% from 0%, placing it between Sonnet 4.6 at 4.2% and Opus 4.6 at 6.6%.
Harvey said post-training also lifted many held-out tasks from roughly 70% pass rates to about 95% and put the model in a similar quality band to leading closed models while costing about one-eighth to one-fiftieth as much per token as Sonnet 4.6 and Opus 4.6. The companies said the result shows a newly launched open model can be turned into a specialized legal agent quickly.
From the sources (4 posts)
@nvidiaaiRT @harvey: We partnered with @trajectorylabs to post-train NVIDIA Nemotron 3 Ultra for legal. Here’s what we found: 1) Open-weight models…
@ctnzrRT @harvey: We partnered with @trajectorylabs to post-train NVIDIA Nemotron 3 Ultra for legal. Here’s what we found: 1) Open-weight models…
@harveyWe partnered with @trajectorylabs to post-train NVIDIA Nemotron 3 Ultra for legal. Here’s what we found: 1) Open-weight models can reach frontier legal performance. On our Legal Agent Benchmark (LAB), Nemotron 3 Ultra started at a 0% all-
@trajectorylabs1/ We post-trained @nvidia Nemotron 3 Ultra on @harvey Legal Agent Bench in under 24 hours. The result: an open model reaching the same band as leading closed models on legal work, at a fraction of the cost. The correlating story: when a