Nemotron 3 Super 120B A12B (Reasoning) vs Qwen3.5 9B (Reasoning)

Which is better for the money: Nemotron 3 Super 120B A12B (Reasoning) by NVIDIA or Qwen3.5 9B (Reasoning) by Alibaba? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-27.

Trade-off

NVIDIANemotron 3 Super 120B A12B (Reasoning)Off the frontier

Intelligence: 12.80
Total cost: $1319

AlibabaQwen3.5 9B (Reasoning)Off the frontier

Intelligence: 11.20
Total cost: $329

Verdict

Depends on your budget

Nemotron 3 Super 120B A12B (Reasoning) scores 1.6 points higher (12.8 vs 11.2) but costs 4.0× as much to run the benchmark ($1319 vs $329; premium vs mid-range cost classes). They are not alternatives at one budget: pick Nemotron 3 Super 120B A12B (Reasoning) when you need intelligence above 11.2, and Qwen3.5 9B (Reasoning) when 11.2 is enough.

Metric	Nemotron 3 Super 120B A12B (Reasoning)	Qwen3.5 9B (Reasoning)	Difference
Intelligence (higher is better)	12.8	11.2	−12.5% Qwen3.5 9B (Reasoning) is 12.5% less intelligent
Total AA cost (lower is better)	$1,318.62	$328.86	−75.1% Qwen3.5 9B (Reasoning) is 75.1% cheaper
End-to-end time (lower is better)	16.78s	43.79s	+161.0% Qwen3.5 9B (Reasoning) is 161.0% slower
Price per 1M tokens (in / out)	$0.30 / $0.90	$0.14 / $0.20
Input modalities	Text	Text, Image, Video

Qwen3.5 9B (Reasoning) vs Nemotron 3 Super 120B A12B (Reasoning): 12.5% less intelligence, 75.1% less cost to run the AA benchmark, and 161.0% slower end-to-end.

Open this matchup in the interactive picker Nemotron 3 Super 120B A12B (Reasoning): what beats it Qwen3.5 9B (Reasoning): what beats it

Today's Pareto frontier

Against the frontier

Nemotron 3 Super 120B A12B (Reasoning) is off the frontier: at the same or lower cost, GPT-6.1 Sol (Max) scores 51.80 for $1082.
Qwen3.5 9B (Reasoning) is off the frontier: at the same or lower cost, MiMo-V2.6-Pro scores 46.30 for $207.

Nemotron 3 Super 120B A12B (Reasoning)Qwen3.5 9B (Reasoning)Today's Pareto frontierOpen-weights frontierEvery other model

Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/nvidia-nemotron-3-super-120b-a12b/qwen3-5-9b · Markdown: /api/v1/compare/nvidia-nemotron-3-super-120b-a12b/qwen3-5-9b?format=md · llms.txt · agent skill