Fine-tuned Nemotron 3.5 matches Opus 4.7 on Harvey legal agent bench at 1/11 the price
simonguozirui · x · 2026-10-16
trajectorylabs trained NVIDIA Nemotron 3.5 Super VL on Harvey's Legal Agent Bench and reports rubric scores level with Opus 4.7 at $1.34/M tokens vs $15.
Per the shared chart: fine-tuned Nemotron scores 86.2%, beating GPT 5.5 (84.1% at $5.62/M) and Opus 4.7 (85.6%), while the untuned base model sits at just 73.2%. A striking case of cheap domain fine-tuning approaching flagship-level agent performance.
More from Models
- Analyst: in a year, models 2-3x better across the board at 10x lower cost, token use up 10-20x — DeryaTR_ · 2026-10-16
- Google revamps Gemma docs, site teases Gemma 4 open models — rseroter · 2026-10-16
- Respan's Span-02 brings anytime reasoning: interrupt it mid-thought and still get the best answer — techNmak · 2026-10-16
- Liquid AI ships d1-ultra decision model, tops Decision Index at 65 across 112 evals — maximelabonne · 2026-10-16
- Meta releases Muse Spark Open: 816B/42B active, 1M context, most capable US open-weight model — AIatMeta · 2026-10-16
- Scale AI's open muse spark model hits seven API platforms, runs on vLLM, SGLang, MLX — alexandr_wang · 2026-10-16