Skip to main content

NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 vs NVIDIA Nemotron 3 Super 120B-A12B

SpecNVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4NVIDIA Nemotron 3 Super 120B-A12B
Respan Index30.9 (#89)19.1 (#135)
Blended price per 1M$0.175$0.197
Context window1M1M
Input / output per 1M$0.1 / $0.4$0.102 / $0.48
Max output--
Inputtext, vision, videotext
Released2026-10-152026-03-11

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryNVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4NVIDIA Nemotron 3 Super 120B-A12B
Coding10.2 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP44.4 NVIDIA Nemotron 3 Super 120B-A12B
Agents39.4 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP417.1* NVIDIA Nemotron 3 Super 120B-A12B
Reasoning33.4 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP423.7 NVIDIA Nemotron 3 Super 120B-A12B
Knowledge & language25.3* NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP417.4 NVIDIA Nemotron 3 Super 120B-A12B
Human preference50.9 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP440.3 NVIDIA Nemotron 3 Super 120B-A12B

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 leads on 2 of the 2 benchmarks both report. Higher is better. Each score links to where it was published.

FAQ

Is NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 better than NVIDIA Nemotron 3 Super 120B-A12B?

NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 scores 30.9 on the Respan Index (#89), ahead of NVIDIA Nemotron 3 Super 120B-A12B at 19.1 (#135). NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 leads on 2 of the 2 benchmarks both report.

Which is cheaper, NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 or NVIDIA Nemotron 3 Super 120B-A12B?

NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 lists at $0.1 input and $0.4 output per 1M tokens; NVIDIA Nemotron 3 Super 120B-A12B at $0.102 and $0.48. NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 is 1.1x cheaper per token at list price.

Which has the larger context window?

Both accept 1M tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.