Skip to main content
Launching the open-source gateway

MiniMax M3 vs NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4

SpecMiniMax M3NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Respan Index31.2 (#76)31.1 (#79)
Blended price per 1M$0.394$0.237
Context window1M1M
Input / output per 1M$0.225 / $0.9$0.15 / $0.5
Max output--
Inputtext, visiontext, vision, video
Released2026-06-012026-10-15

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.

CategoryMiniMax M3NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Coding9.4 MiniMax M310.5 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Agents47.3 MiniMax M340.5 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Reasoning23.0 MiniMax M332.8 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Knowledge & language33.4 MiniMax M325.7* NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
Human preference52.7 MiniMax M350.3 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4

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

Benchmarks both report

MiniMax M3 leads on 5 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkMiniMax M3NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
LMArena Agent (LMArena)-0.1016-0.1494
LMArena Elo14391412
LMArena WebDev (LMArena)14831399
LMArena Vision (LMArena)12331204
GPQA Diamond90.9%89.9%

FAQ

Is MiniMax M3 better than NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4?

MiniMax M3 scores 31.2 on the Respan Index (#76), ahead of NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 at 31.1 (#79). MiniMax M3 leads on 5 of the 5 benchmarks both report.

Which is cheaper, MiniMax M3 or NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4?

MiniMax M3 lists at $0.225 input and $0.9 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 1.7x 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.