LLM-as-a-Verifier lifts Nemotron 3.5 Super by 9-10 points on agentic benchmarks
simonguozirui · x · 2026-10-16
NVIDIA's latest Nemotron 3.5 Super adopts an LLM-as-a-Verifier approach: the same model acts as both generator and verifier, sampling 5 candidate solutions and picking the best one with the LLM.
Gains on agentic benchmarks are substantial:
- Terminal-Bench 2.1: 62.7% → 71.9% (+9%)
- DeepSWE: 24.6% → 34.5% (+10%)
The team credits NVIDIA for compute resources and collaboration; details are in the Nemotron 3.5 model card.
More from Models
- Nolla Health Post-Trains Nemotron 3.5 VL: Visual Diagnosis Jumps from 35% to 66.8% — LoganGrasby · 2026-10-16
- Dev argues coding models now beat nearly all engineers in every branch of software — zack_overflow · 2026-10-16
- Prediction: Chinese frontier models could match GPT-6 by March 2027 — teortaxesTex · 2026-10-16
- Liquid AI's d1-ultra, #1 on Artificial Analysis Decision Index, lands on Vercel — JosephJacks_ · 2026-10-16
- Weekly AI roundup: Claude Haiku 5.5 cuts prices ~90%, Gemini 4 Argon output jumps to 1M tokens — DeepLearningAI · 2026-10-16
- Tencent Hunyuan says reported agent activity came from third-party model evals, not deliberate targeting — TencentHunyuan · 2026-10-16