Compare/NVIDIA Nemotron Nano 9B V2 (Non-reasoning) vs gpt-oss-20B (low)

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)vsgpt-oss-20B (low)

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

NVIDIA

NVIDIA Nemotron Nano 9B V2 (Non-reasoning)

Input
$0.05/M
Output
$0.195/M
Speed
157 tok/s
TTFT
0.60s
OpenAI

gpt-oss-20B (low)

Input
$0.06/M
Output
$0.2/M
Speed
321 tok/s
TTFT
0.46s

Winner by Category

Cheaper
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
Faster (tok/s)
gpt-oss-20B (low)
Lower Latency
gpt-oss-20B (low)
Benchmarks (2-7)
gpt-oss-20B (low)

Pricing Comparison

MetricNVIDIA Nemotron Nano 9B V2 (Non-reasoning)gpt-oss-20B (low)
Input ($/M tokens)$0.05$0.06
Output ($/M tokens)$0.195$0.2
Cost for 1M input + 100K output tokens:
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)$0.07
gpt-oss-20B (low)$0.08

Speed Comparison

Output Speed (tokens/s) — higher is better
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
157 tok/s
gpt-oss-20B (low)
321 tok/s
Time to First Token (seconds) — lower is better
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
0.60s
gpt-oss-20B (low)
0.46s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
13.220.8
Coding Index
7.514.4
Math Index
62.362.3
GPQA Diamond
55.7%61.1%
MMLU-Pro
73.9%71.8%
LiveCodeBench
70.1%65.2%
AIME 2025
62.3%62.3%
MATH-500
Humanity's Last Exam
4.0%5.1%
SciCode
20.9%34.0%
IFBench
27.1%57.8%
TerminalBench
0.8%4.5%
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)2 wins
7 winsgpt-oss-20B (low)

Frequently Asked Questions

Which is cheaper, NVIDIA Nemotron Nano 9B V2 (Non-reasoning) or gpt-oss-20B (low)?

NVIDIA Nemotron Nano 9B V2 (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.09/M tokens vs $0.09/M for gpt-oss-20B (low).

Which model performs better on benchmarks?

gpt-oss-20B (low) wins 7 out of 12 benchmarks compared to 2 for NVIDIA Nemotron Nano 9B V2 (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

gpt-oss-20B (low) generates tokens faster at 321 tok/s vs 157 tok/s. However, gpt-oss-20B (low) has lower time-to-first-token (0.46s vs 0.60s).

When should I use NVIDIA Nemotron Nano 9B V2 (Non-reasoning) vs gpt-oss-20B (low)?

Choose based on your priorities: NVIDIA Nemotron Nano 9B V2 (Non-reasoning) for lower cost, gpt-oss-20B (low) for stronger benchmark performance, and gpt-oss-20B (low) for faster generation. For latency-sensitive apps, check the TTFT comparison above.