NVIDIA ships Nemotron-3.5-Super-VL: 120B/12B-active VLM beats Ultra-3.0 on benchmarks
kuchaev · x · 2026-10-15
NVIDIA's Nemotron-3.5-Super-VL is out, and the author claims it beats Ultra-3.0 on most benchmarks.
- Same base architecture as Super-3.0: 120B total parameters, 12B active, plus a vision encoder, now with visual reasoning
- Key scores: SWEBench-Pro 51.79%, AA index of 26 vs 23 for Ultra-3.0
- The post-training pipeline was greatly simplified: fewer teachers and a smaller SFT set, with significantly improved data and environment quality, extended to multimodal. The attached diagram shows the full flow: multimodal SFT, text-only trunk RL, then MOPD two-stage teacher merging into final weights.
More from Models
- OpenAI ships GPT-Live-1.1: new voices in six languages, fewer confirmations — OpenAI · 2026-10-16
- Muse Spark model appears on LMArena, testable in Battle and Agent modes — arena · 2026-10-16
- Running a multi-model UI design arena: Paseo orchestrates four design drafts per model — vista8 · 2026-10-16
- Ilya Sutskever questions Meta license clause taxing MaaS providers above $20M revenue — ilyasu · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- Midas flags inconsistent Claude limits: 33% weekly and 45% window usage despite $100 credits, yet out of API credits — TheMoonMidas · 2026-10-16