Skip to main content
Launching the open-source gateway

Claude Sonnet 5.5 vs NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4

SpecClaude Sonnet 5.5NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Respan Index73.1 (#2)31.1 (#79)
Blended price per 1M$2$0.237
Context window1M1M
Input / output per 1M$1 / $5$0.15 / $0.5
Max output128K-
Inputtext, visiontext, vision, video
Released2026-09-282026-10-15

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.

CategoryClaude Sonnet 5.5NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Coding79.6 Claude Sonnet 5.510.5 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Agents78.4 Claude Sonnet 5.540.5 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Reasoning79.0 Claude Sonnet 5.532.8 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Knowledge & language48.5 Claude Sonnet 5.525.7* NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Human preference60.2 Claude Sonnet 5.550.3 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4

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

Benchmarks both report

Claude Sonnet 5.5 leads on 5 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Sonnet 5.5NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
LMArena Agent (LMArena)0.1384-0.1494
LMArena Elo14771412
LMArena WebDev (LMArena)17701399
LMArena Vision (LMArena)12651204
GPQA Diamond95.6%89.9%

FAQ

Is Claude Sonnet 5.5 better than NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4?

Claude Sonnet 5.5 scores 73.1 on the Respan Index (#2), ahead of NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 at 31.1 (#79). Claude Sonnet 5.5 leads on 5 of the 5 benchmarks both report.

Which is cheaper, Claude Sonnet 5.5 or NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4?

Claude Sonnet 5.5 lists at $1 input and $5 output per 1M tokens; NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 at $0.15 and $0.5. NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 is 8.4x 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.