NVIDIA Nemotron 3 Super 120B A12B vs NVIDIA Nemotron 3.5 Lightning

Close to a tie overall. NVIDIA Nemotron 3.5 Lightning costs 46% less for the same work, and both read a 256K-token context.

Model A

NVIDIA Nemotron 3 Super 120B A12B

by NVIDIA · #48 of 67 overall

Coming soon · price at launch

Context: 256K
Input / 1M: $0.075
Output / 1M: $0.40

Model B

NVIDIA Nemotron 3.5 Lightning

by NVIDIA · #47 of 67 overall

Coming soon · price at launch

Context: 256K
Input / 1M: $0.060
Output / 1M: $0.16

Better overall

About even

Grade 50.3 vs 50.7

Cheaper

NVIDIA Nemotron 3.5 Lightning

46% less, $0.085 vs $0.16 blended

Larger context

Same

256K vs 256K tokens

SWE-bench Verified

NVIDIA Nemotron 3 Super 120B A12B

60.5% vs 51.6%

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

NVIDIA Nemotron 3 Super 120B A12B1,360

NVIDIA Nemotron 3.5 Lightning1,351

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

NVIDIA Nemotron 3 Super 120B A12B1,407

NVIDIA Nemotron 3.5 Lightning1,425

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

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

NVIDIA Nemotron 3.5 Lightning51.6%^v

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

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

NVIDIA Nemotron 3.5 Lightning24.6%^v

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

NVIDIA Nemotron 3 Super 120B A12B31%^v

NVIDIA Nemotron 3.5 Lightning—

NVIDIA Nemotron 3 Super 120B A12BNVIDIA Nemotron 3.5 Lightningv = 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

NVIDIA Nemotron 3 Super 120B A12B$31.00 /month

NVIDIA Nemotron 3.5 Lightning$18.40 /month

NVIDIA Nemotron 3.5 Lightning saves you $12.60 a month at this usage, $151 a year.

At a glance

Attribute	NVIDIA Nemotron 3 Super 120B A12B	NVIDIA Nemotron 3.5 Lightning
Made by	NVIDIA	NVIDIA
Availability	Coming soon	Coming soon
Overall grade	Good · 50.3	Good · 50.7
Overall rank	#48 of 67	#47 of 67
Input price	$0.075 per 1M	$0.060 per 1M
Output price	$0.40 per 1M	$0.16 per 1M
Context window	262,144 tokens	262,144 tokens
Reasoning levels	No	No
Reads images	No	No
Model ID	nvidia-nemotron-3-super-120b-a12b	nvidia-nemotron-3.5-lightning

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": "nvidia-nemotron-3-super-120b-a12b", "messages": [...]}'

# …then swap one word
  -d '{"model": "nvidia-nemotron-3.5-lightning", "messages": [...]}'

Questions

Is NVIDIA Nemotron 3 Super 120B A12B or NVIDIA Nemotron 3.5 Lightning better?

They grade within two points of each other (50.3 and 50.7), so pick on price and the benchmarks that match your work.

Which is cheaper, NVIDIA Nemotron 3 Super 120B A12B or NVIDIA Nemotron 3.5 Lightning?

NVIDIA Nemotron 3.5 Lightning: $0.060 in and $0.16 out per million tokens, against $0.075 and $0.40 through FullsendAI.

Which has the larger context window?

Neither: both take 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), SWE-bench, Terminal-Bench, and model makers’ published results where marked v. Prices are FullsendAI’s, per million tokens. Data as of Oct 28, 2026.