NVIDIA's Nemotron 3.5 Super VL scores 26 to become top US open-weight model; Bolt 74B nears Ultra at 1/7 the params
ArtificialAnlys · x · 2026-10-15
Artificial Analysis covers NVIDIA's dual release. Nemotron 3.5 Super VL (120B total / 12B active, 1M context, vision+text input) scores 26.5 on the Intelligence Index, making it the leading US open-weight model, edging out Thinking Machines' Inkling Small (25.7) and NVIDIA's prior flagship Nemotron 3 Ultra (23). It delivers twice the intelligence of Nemotron 3 Super (13) using 60% fewer output tokens per task, and its NVFP4 build is near lossless, within 0.1 points of BF16.
Nemotron 3.5 Bolt 74B-A9B (256k context), first in the new Bolt family, scores 21 — within 1.5 points of the 550B Nemotron 3 Ultra with about a seventh of its parameters. It burns 82k output tokens per task, 1.8× Super VL's 46k.
The US still trails on open-weight intelligence: UAE's K2 Horizon (31) and China's MiMo-V2.6-Pro (46) rank higher.
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