Compare models

1 model side by side

Add a second model above to see them side by side.
nvidia/nemotron-3-120b-a12b
Details
Overview
DescriptionNVIDIA's Mixture-of-Experts model with 120B total parameters and 12B active, optimized for efficient inference with strong reasoning capabilities.
Authornvidia
CategoryText Generation
Context length131K
Providers2
Pricing (per 1M tokens)
Input$0.10
Output$0.30
Capabilities
Reasoning
Tool calling
Vision
Streaming
Token activity (30 days)
Usage
Artificial Analysis
Intelligence36.0
Coding31.2
Benchmarks
GPQA Diamond0.8
HLE0.2
IFEval0.7