Skip to main content

DeepSeek V3.1 vs NVIDIA Nemotron 3 Super 120B-A12B

SpecDeepSeek V3.1NVIDIA Nemotron 3 Super 120B-A12B
Respan Index18.9 (#136)19.1 (#134)
Blended price per 1M$0.425$0.197
Context window128K1M
Input / output per 1M$0.25 / $0.95$0.102 / $0.48
Max output--
Inputtexttext
Released2025-08-212026-03-11

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.

CategoryDeepSeek V3.1NVIDIA Nemotron 3 Super 120B-A12B
Coding4.6 DeepSeek V3.14.4 NVIDIA Nemotron 3 Super 120B-A12B
Agents10.9 DeepSeek V3.117.1* NVIDIA Nemotron 3 Super 120B-A12B
Reasoning25.6 DeepSeek V3.123.7 NVIDIA Nemotron 3 Super 120B-A12B
Knowledge & language14.5* DeepSeek V3.117.3 NVIDIA Nemotron 3 Super 120B-A12B
Human preference47.9 DeepSeek V3.140.3 NVIDIA Nemotron 3 Super 120B-A12B

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

Benchmarks both report

DeepSeek V3.1 leads on 3 of the 3 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkDeepSeek V3.1NVIDIA Nemotron 3 Super 120B-A12B
LMArena Elo14171360
AIME 202590.8%90.2%
WeirdML (Håvard Tveit Ihle)38.4%38%

FAQ

Is DeepSeek V3.1 better than NVIDIA Nemotron 3 Super 120B-A12B?

NVIDIA Nemotron 3 Super 120B-A12B scores 19.1 on the Respan Index (#134), ahead of DeepSeek V3.1 at 18.9 (#136). DeepSeek V3.1 leads on 3 of the 3 benchmarks both report.

Which is cheaper, DeepSeek V3.1 or NVIDIA Nemotron 3 Super 120B-A12B?

DeepSeek V3.1 lists at $0.25 input and $0.95 output per 1M tokens; NVIDIA Nemotron 3 Super 120B-A12B at $0.102 and $0.48. NVIDIA Nemotron 3 Super 120B-A12B is 2.2x cheaper per token at list price.

Which has the larger context window?

DeepSeek V3.1 accepts 128K tokens and NVIDIA Nemotron 3 Super 120B-A12B 1M tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.