Mercor Post-Trains Nemotron with Targeted APEX Data, Gains Across Law, SWE, Accounting
NVIDIAAI · x · 2026-10-17
NVIDIA shared Mercor's announcement: alongside the Nemotron 3.5 Super VL launch, Mercor worked with Ramp, Harvey, Cognition and the NVIDIA team to post-train the model using targeted datasets from its APEX benchmarks.
The post-trained Nemotron was evaluated on legal, software engineering, and accounting tasks it had never seen, and improved across all three professional domains. Full results are available in their published report.
More from Models
- Hash Rate Ep. 189: Jev models on Bittensor subnet SN92, decentralized training vs traditional LLMs — markjeffrey · 2026-10-17
- 'Remove AI tics and mannered prose': a one-line prompt fix for Argon's writing — arjunrajlab · 2026-10-17
- Blind test of 200 real image edits: nano banana pro loses to its cheaper base model — ravisparikh · 2026-10-17
- Dev ditches Gemini 4 Argon for Grok 4.5, which eats 96.6% of his Cursor tokens — gaganghotra_ · 2026-10-17
- LMArena opens Code Arena WebDev for blind head-to-head model coding battles — arena · 2026-10-17
- Unverified: GPT-6 Pro said to launch parallel research subagents, 50-100 weekly messages — TheMoonMidas · 2026-10-17