New post-training run lifts NVIDIA Nemotron's AutomationBench from 14.8% to 27.5%
echen · x · 2026-10-31
echen reports a new post-training run on NVIDIA's Nemotron lifted AutomationBench from 14.8% to 27.5% — a 12.7pp gain, nearly doubling the score.
No methodology or cost details were disclosed, though the result lands alongside ongoing RL rollout optimization work on Nemotron 3.5 Lightning by You.com, NVIDIA, and CoreWeave.
More from Models
- Arena weekly: Gemini 4 Carbon tops Text Arena, GPT-6.1 Terra enters Agent Arena at #8 — arena · 2026-10-31
- 6 October models, same 5 trap-laden agent tasks: DeepSeek does it all for $0.02, hyped Flint passes 1/5 — latent_lurker8587 · 2026-10-31
- Security researcher: air-gapped AI agents are only possible with open-weight models — wunderwuzzi23 · 2026-10-31
- Gemini 4 Carbon tops Artificial Analysis index at 59, 23% cheaper per task than Opus 5.5 — rohanpaul_ai · 2026-10-31
- Podcast: Is Mistral Large 4 the West's best open model? Plus AI cyber threats — The Cognitive Revolution · 2026-10-31
- OpenAI shows GPT-6 Astra remotely controlling a robot arm in builder community — OpenAIDevs · 2026-10-31