DeepSeek V3 vs NVIDIA Nemotron 3 Super 120B A12B

NVIDIA Nemotron 3 Super 120B A12B grades higher overall (50.3 against 47.5). NVIDIA Nemotron 3 Super 120B A12B costs 65% less for the same work.

Model A

DeepSeek V3

by DeepSeek · #51 of 67 overall

Coming soon · price at launch

Context: 160K
Input / 1M: $0.32
Output / 1M: $0.89

Model B

NVIDIA Nemotron 3 Super 120B A12B

by NVIDIA · #48 of 67 overall

Coming soon · price at launch

Context: 256K
Input / 1M: $0.085
Output / 1M: $0.40

Better overall

NVIDIA Nemotron 3 Super 120B A12B

Grade 47.5 vs 50.3

Cheaper

NVIDIA Nemotron 3 Super 120B A12B

65% less, $0.16 vs $0.46 blended

Larger context

NVIDIA Nemotron 3 Super 120B A12B

160K vs 256K tokens

SWE-bench Verified

NVIDIA Nemotron 3 Super 120B A12B

42% vs 60.5%

Head to head

Public benchmarks. Longer is better; each value links to its source.

LMArena TextElo-style rating · LMArena (CC BY 4.0) · Oct 15, 2026

DeepSeek V31,358

NVIDIA Nemotron 3 Super 120B A12B1,360

LMArena CodingElo-style rating · LMArena (CC BY 4.0) · Oct 15, 2026

DeepSeek V31,387

NVIDIA Nemotron 3 Super 120B A12B1,407

Aider Polyglot% of exercises solved · Aider (aider.chat) · Dec 25, 2024

DeepSeek V348.4%

NVIDIA Nemotron 3 Super 120B A12B—

SWE-bench Verified% of issues resolved · SWE-bench · Mar 11, 2026 · reference

DeepSeek V342%^v

NVIDIA Nemotron 3 Super 120B A12B60.5%^v

Terminal-Bench 2.1% of tasks passed · Terminal-Bench · Aug 11, 2026 · reference

DeepSeek V3—

NVIDIA Nemotron 3 Super 120B A12B39.6%^v

Terminal-Bench 2.0% of tasks passed · Terminal-Bench · Mar 11, 2026 · reference

DeepSeek V3—

NVIDIA Nemotron 3 Super 120B A12B31%^v

LiveCodeBenchpass@1, % · LiveCodeBench · Dec 25, 2024 · reference

DeepSeek V340.5%^v

NVIDIA Nemotron 3 Super 120B A12B—

DeepSeek V3NVIDIA Nemotron 3 Super 120B A12Bv = reported by the model’s maker. — = no public score yet. Arena bars span the range across every model we grade.

What it costs you

Drag to match your monthly usage.

Input tokens a month200MOutput tokens a month40M

DeepSeek V3$99.60 /month

NVIDIA Nemotron 3 Super 120B A12B$33.00 /month

NVIDIA Nemotron 3 Super 120B A12B saves you $66.60 a month at this usage, $799 a year.

At a glance

Attribute	DeepSeek V3	NVIDIA Nemotron 3 Super 120B A12B
Made by	DeepSeek	NVIDIA
Availability	Coming soon	Coming soon
Overall grade	Good · 47.5	Good · 50.3
Overall rank	#51 of 67	#48 of 67
Input price	$0.32 per 1M	$0.085 per 1M
Output price	$0.89 per 1M	$0.40 per 1M
Context window	163,840 tokens	262,144 tokens
Reasoning levels	No	No
Reads images	No	No
Model ID	deepseek-v3	nvidia-nemotron-3-super-120b-a12b

Try both with one key

Same endpoint, same key, both hosted in the USA. Change one word to switch models, in Claude Code, Cursor, Cline or your own code.

Get your API key

# Ask either model the same thing
curl https://fullsendai.com/v1/chat/completions \
  -H "Authorization: Bearer $FULLSEND_API_KEY" \
  -d '{"model": "deepseek-v3", "messages": [...]}'

# …then swap one word
  -d '{"model": "nvidia-nemotron-3-super-120b-a12b", "messages": [...]}'

Questions

Is DeepSeek V3 or NVIDIA Nemotron 3 Super 120B A12B better?

NVIDIA Nemotron 3 Super 120B A12B grades 50.3 against 47.5 for DeepSeek V3, from public benchmarks.

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

NVIDIA Nemotron 3 Super 120B A12B: $0.085 in and $0.40 out per million tokens, against $0.32 and $0.89 through FullsendAI.

Which has the larger context window?

NVIDIA Nemotron 3 Super 120B A12B, with 262,144 tokens.

Can I use both with one API key?

Yes, once they launch: both are coming soon, at the prices shown, and both will use the same FullsendAI key.

Model rankings All benchmarks Compare other models

Scores: LMArena (CC BY 4.0), Aider (aider.chat), SWE-bench, Terminal-Bench, LiveCodeBench, and model makers’ published results where marked v. Prices are FullsendAI’s, per million tokens. Data as of Oct 28, 2026.