Price Per TokenPrice Per Token
Nvidia
Nvidia
vs
Qwen
Qwen

Nemotron-3 Super 120B A12B vs Qwen3 Next 80B A3B Instruct

A detailed comparison of pricing, benchmarks, and capabilities

Get our weekly newsletter on pricing changes, new releases, and tools.

Join the Price Per Token Community

Key Takeaways

Nemotron-3 Super 120B A12B wins:

  • Cheaper output tokens
  • Higher intelligence benchmark
  • Better at coding

Qwen3 Next 80B A3B Instruct wins:

  • Cheaper input tokens
  • Larger context window
  • Faster response time
  • Better at math
  • Supports tool calls
Price Advantage
Nemotron-3 Super 120B A12B
Benchmark Advantage
Nemotron-3 Super 120B A12B
Context Window
Qwen3 Next 80B A3B Instruct
Speed
Qwen3 Next 80B A3B Instruct

Pricing Comparison

Benchmark Comparison

Context & Performance

Capabilities

Feature Comparison

FeatureNemotron-3 Super 120B A12BQwen3 Next 80B A3B Instruct
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyNemotron-3 Super 120B A12BQwen3 Next 80B A3B Instruct
LicenseProprietaryOpen Source
AuthorNvidiaQwen
ReleasedUnknownSep 2025

Nemotron-3 Super 120B A12B Modalities

Input
Output

Qwen3 Next 80B A3B Instruct Modalities

Input
text
Output
text

Frequently Asked Questions

Qwen3 Next 80B A3B Instruct has cheaper input pricing at $0.09/M tokens. Nemotron-3 Super 120B A12B has cheaper output pricing at $0.50/M tokens.
Nemotron-3 Super 120B A12B scores higher on coding benchmarks with a score of 31.2, compared to Qwen3 Next 80B A3B Instruct's score of 15.3.