Compare/Llama 3.2 Instruct 90B (Vision) vs NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

Llama 3.2 Instruct 90B (Vision)vsNVIDIA Nemotron 3 Super 120B A12B (Reasoning)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Meta

Llama 3.2 Instruct 90B (Vision)

Input
$0.72/M
Output
$0.72/M
Speed
42 tok/s
TTFT
0.37s
NVIDIA

NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

Input
$0.3/M
Output
$0.75/M
Speed
370 tok/s
TTFT
0.55s

Winner by Category

Cheaper
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
Faster (tok/s)
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
Lower Latency
Llama 3.2 Instruct 90B (Vision)
Benchmarks (3-7)
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

Pricing Comparison

MetricLlama 3.2 Instruct 90B (Vision)NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
Input ($/M tokens)$0.72$0.3
Output ($/M tokens)$0.72$0.75
Cost for 1M input + 100K output tokens:
Llama 3.2 Instruct 90B (Vision)$0.79
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)$0.38

Speed Comparison

Output Speed (tokens/s) — higher is better
Llama 3.2 Instruct 90B (Vision)
42 tok/s
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
370 tok/s
Time to First Token (seconds) — lower is better
Llama 3.2 Instruct 90B (Vision)
0.37s
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
0.55s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
11.936.0
Coding Index
31.2
Math Index
GPQA Diamond
43.2%80.0%
MMLU-Pro
67.1%
LiveCodeBench
21.4%
AIME 2025
MATH-500
62.9%
Humanity's Last Exam
4.9%19.2%
SciCode
24.0%36.0%
IFBench
71.5%
TerminalBench
28.8%
Llama 3.2 Instruct 90B (Vision)3 wins
7 winsNVIDIA Nemotron 3 Super 120B A12B (Reasoning)

Frequently Asked Questions

Which is cheaper, Llama 3.2 Instruct 90B (Vision) or NVIDIA Nemotron 3 Super 120B A12B (Reasoning)?

NVIDIA Nemotron 3 Super 120B A12B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.41/M tokens vs $0.72/M for Llama 3.2 Instruct 90B (Vision).

Which model performs better on benchmarks?

NVIDIA Nemotron 3 Super 120B A12B (Reasoning) wins 7 out of 12 benchmarks compared to 3 for Llama 3.2 Instruct 90B (Vision). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

NVIDIA Nemotron 3 Super 120B A12B (Reasoning) generates tokens faster at 370 tok/s vs 42 tok/s. Llama 3.2 Instruct 90B (Vision) also has lower time-to-first-token (0.37s vs 0.55s).

When should I use Llama 3.2 Instruct 90B (Vision) vs NVIDIA Nemotron 3 Super 120B A12B (Reasoning)?

Choose based on your priorities: NVIDIA Nemotron 3 Super 120B A12B (Reasoning) for lower cost, NVIDIA Nemotron 3 Super 120B A12B (Reasoning) for stronger benchmark performance, and NVIDIA Nemotron 3 Super 120B A12B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.