Compare/gpt-oss-20B (high) vs NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

gpt-oss-20B (high)vsNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

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

OpenAI

gpt-oss-20B (high)

Input
$0.06/M
Output
$0.2/M
Speed
316 tok/s
TTFT
0.41s
NVIDIA

NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

Input
$0.05/M
Output
$0.2/M
Speed
80 tok/s
TTFT
0.29s

Winner by Category

Cheaper
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
Faster (tok/s)
gpt-oss-20B (high)
Lower Latency
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
Benchmarks (10-1)
gpt-oss-20B (high)

Pricing Comparison

Metricgpt-oss-20B (high)NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
Input ($/M tokens)$0.06$0.05
Output ($/M tokens)$0.2$0.2
Cost for 1M input + 100K output tokens:
gpt-oss-20B (high)$0.08
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)$0.07

Speed Comparison

Output Speed (tokens/s) — higher is better
gpt-oss-20B (high)
316 tok/s
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
80 tok/s
Time to First Token (seconds) — lower is better
gpt-oss-20B (high)
0.41s
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
0.29s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
24.513.2
Coding Index
18.515.8
Math Index
89.313.3
GPQA Diamond
68.8%39.9%
MMLU-Pro
74.8%57.9%
LiveCodeBench
77.7%36.0%
AIME 2025
89.3%13.3%
MATH-500
Humanity's Last Exam
9.8%4.6%
SciCode
34.4%23.0%
IFBench
65.1%37.5%
TerminalBench
10.6%12.1%
gpt-oss-20B (high)10 wins
1 winsNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

Frequently Asked Questions

Which is cheaper, gpt-oss-20B (high) or NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)?

NVIDIA Nemotron 3 Nano 30B A3B (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 (high).

Which model performs better on benchmarks?

gpt-oss-20B (high) wins 10 out of 12 benchmarks compared to 1 for NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

gpt-oss-20B (high) generates tokens faster at 316 tok/s vs 80 tok/s. However, NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) has lower time-to-first-token (0.29s vs 0.41s).

When should I use gpt-oss-20B (high) vs NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)?

Choose based on your priorities: NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) for lower cost, gpt-oss-20B (high) for stronger benchmark performance, and gpt-oss-20B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.