Llama 3.3 Nemotron Super 49B v1 (Reasoning) vs NVIDIA Nemotron Nano 9B V2 (Reasoning)

Comparing 2 AI models · 6 benchmarks · NVIDIA

Most Affordable
NVIDIA logo
Llama 3.3 Nemotron Super 49B v1 (Reasoning)
$0.00/1M
Highest Intelligence
NVIDIA logo
Llama 3.3 Nemotron Super 49B v1 (Reasoning)
64.3% GPQA
Best for Coding
NVIDIA logo
NVIDIA Nemotron Nano 9B V2 (Reasoning)
31.9 Coding Index
Price Difference
Infinityx
input cost range

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Benchmark Winners

6 tests
NVIDIA logo

Llama 3.3 Nemotron Super 49B v1 (Reasoning)

4
  • GPQA
  • MMLU Pro
  • HLE
  • MATH 500
NVIDIA logo

NVIDIA Nemotron Nano 9B V2 (Reasoning)

2
  • LiveCodeBench
  • AIME 2025
Metric
NVIDIA logo Llama 3.3 Nemotron Super 49B v1 (Reasoning)
NVIDIA
NVIDIA logo NVIDIA Nemotron Nano 9B V2 (Reasoning)
NVIDIA
Pricing
Per 1M tokens
Input Cost $0.00/1M $0.04/1M
Output Cost $0.00/1M $0.16/1M
Blended Cost 3:1 input/output ratio
$0.07/1M
Specifications
Organization Model creator
NVIDIA NVIDIA
Release Date Launch date
Mar 18, 2025 Aug 18, 2025
Performance & Speed
Throughput Output speed
95.1 tok/s
Time to First Token (TTFT) Initial response delay
225ms
Latency Time to first answer token
21261ms
Composite Indices
Intelligence Index Overall reasoning capability
35.5 37.2
Coding Index Programming ability
18.7 31.9
Math Index Mathematical reasoning