Post-Trained Nemotron 3.5 Hits Opus-Level on Legal Tasks, Halves Token Use
sudoraohacker · x · 2026-08-12
Harvey, in collaboration with NVIDIA and Trajectory Labs, post-trained the Nemotron 3.5 Lightning model on the Legal Agent Bench (LAB).
Key findings from the post-training:
- Performance on held-out LAB tasks improved from 0% to 8.3%, achieving Opus-level all pass and even beating the much larger post-trained Nemotron 3 Ultra.
- Performance improved across nine practice areas with zero regressions.
- The model's average output length was reduced from 90k to 37k tokens, increasing the reward-per-token by 2.4x.
Related event: Post-Trained NVIDIA Model Matches Claude Opus in Legal Tasks(2 posts)→
More from coding & agent
- Developer Reflections: Shipping Code Effectively Without Subagents — zeeg · 2026-08-12
- Give AI Agents 3Blue1Brown Animation Skills with manim_skill — tom_doerr · 2026-08-12
- pi-shepherdr: Orchestrate Multi-Agents with a 271-Token Surface — solyarisoftware · 2026-08-12
- AI Coding Assistant Tuning Fail: Turning Codex into a Paper Machine — burny_tech · 2026-08-12
- Coinbase Payments Update Enables AI Agents to Transact Directly — kleffew94 · 2026-08-12
- Opinion: The Role of Compilers Will Change Heavily in the AI Era — pranjalssh · 2026-08-12