Compare/Qwen3 30B A3B (Non-reasoning) vs NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

Qwen3 30B A3B (Non-reasoning)vsNVIDIA Nemotron 3 Super 120B A12B (Reasoning)

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

Alibaba

Qwen3 30B A3B (Non-reasoning)

Input
$0.2/M
Output
$0.8/M
Speed
68 tok/s
TTFT
1.02s
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
Qwen3 30B A3B (Non-reasoning)
Faster (tok/s)
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
Lower Latency
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
Benchmarks (5-7)
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)

Pricing Comparison

MetricQwen3 30B A3B (Non-reasoning)NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
Input ($/M tokens)$0.2$0.3
Output ($/M tokens)$0.8$0.75
Cost for 1M input + 100K output tokens:
Qwen3 30B A3B (Non-reasoning)$0.28
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)$0.38

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3 30B A3B (Non-reasoning)
68 tok/s
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
370 tok/s
Time to First Token (seconds) — lower is better
Qwen3 30B A3B (Non-reasoning)
1.02s
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
0.55s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
12.536.0
Coding Index
13.331.2
Math Index
21.7
GPQA Diamond
51.5%80.0%
MMLU-Pro
71.0%
LiveCodeBench
32.2%
AIME 2025
21.7%
MATH-500
86.3%
Humanity's Last Exam
4.6%19.2%
SciCode
26.4%36.0%
IFBench
31.9%71.5%
TerminalBench
6.8%28.8%
Qwen3 30B A3B (Non-reasoning)5 wins
7 winsNVIDIA Nemotron 3 Super 120B A12B (Reasoning)

Frequently Asked Questions

Which is cheaper, Qwen3 30B A3B (Non-reasoning) or NVIDIA Nemotron 3 Super 120B A12B (Reasoning)?

Qwen3 30B A3B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.35/M tokens vs $0.41/M for NVIDIA Nemotron 3 Super 120B A12B (Reasoning).

Which model performs better on benchmarks?

NVIDIA Nemotron 3 Super 120B A12B (Reasoning) wins 7 out of 12 benchmarks compared to 5 for Qwen3 30B A3B (Non-reasoning). 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 68 tok/s. However, NVIDIA Nemotron 3 Super 120B A12B (Reasoning) has lower time-to-first-token (0.55s vs 1.02s).

When should I use Qwen3 30B A3B (Non-reasoning) vs NVIDIA Nemotron 3 Super 120B A12B (Reasoning)?

Choose based on your priorities: Qwen3 30B A3B (Non-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.