Compare/gpt-oss-120B (high) vs NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

gpt-oss-120B (high)vsNVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

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

OpenAI

gpt-oss-120B (high)

Input
$0.15/M
Output
$0.6/M
Speed
253 tok/s
TTFT
0.49s
NVIDIA

NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

Input
$0.2/M
Output
$0.6/M
Speed
138 tok/s
TTFT
0.53s

Winner by Category

Cheaper
gpt-oss-120B (high)
Faster (tok/s)
gpt-oss-120B (high)
Lower Latency
gpt-oss-120B (high)
Benchmarks (11-0)
gpt-oss-120B (high)

Pricing Comparison

Metricgpt-oss-120B (high)NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
Input ($/M tokens)$0.15$0.2
Output ($/M tokens)$0.6$0.6
Cost for 1M input + 100K output tokens:
gpt-oss-120B (high)$0.21
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)$0.26

Speed Comparison

Output Speed (tokens/s) — higher is better
gpt-oss-120B (high)
253 tok/s
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
138 tok/s
Time to First Token (seconds) — lower is better
gpt-oss-120B (high)
0.49s
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
0.53s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
33.310.1
Coding Index
28.65.9
Math Index
93.426.7
GPQA Diamond
78.2%43.9%
MMLU-Pro
80.8%64.9%
LiveCodeBench
87.8%34.5%
AIME 2025
93.4%26.7%
MATH-500
Humanity's Last Exam
18.5%4.5%
SciCode
38.9%17.6%
IFBench
69.0%25.9%
TerminalBench
23.5%0.0%
gpt-oss-120B (high)11 wins
0 winsNVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)

Frequently Asked Questions

Which is cheaper, gpt-oss-120B (high) or NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)?

gpt-oss-120B (high) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.26/M tokens vs $0.30/M for NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning).

Which model performs better on benchmarks?

gpt-oss-120B (high) wins 11 out of 12 benchmarks compared to 0 for NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

gpt-oss-120B (high) generates tokens faster at 253 tok/s vs 138 tok/s. gpt-oss-120B (high) also has lower time-to-first-token (0.49s vs 0.53s).

When should I use gpt-oss-120B (high) vs NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)?

Choose based on your priorities: gpt-oss-120B (high) for lower cost, gpt-oss-120B (high) for stronger benchmark performance, and gpt-oss-120B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.