Compare/Nemotron Cascade 2 30B A3B vs gpt-oss-120B (high)

Nemotron Cascade 2 30B A3Bvsgpt-oss-120B (high)

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

NVIDIA

Nemotron Cascade 2 30B A3B

Input
$0/M
Output
$0/M
Speed
TTFT
OpenAI

gpt-oss-120B (high)

Input
$0.15/M
Output
$0.6/M
Speed
276 tok/s
TTFT
0.48s

Winner by Category

Cheaper
Nemotron Cascade 2 30B A3B
Faster (tok/s)
gpt-oss-120B (high)
Lower Latency
Nemotron Cascade 2 30B A3B
Benchmarks (1-10)
gpt-oss-120B (high)

Pricing Comparison

MetricNemotron Cascade 2 30B A3Bgpt-oss-120B (high)
Input ($/M tokens)$0$0.15
Output ($/M tokens)$0$0.6
Cost for 1M input + 100K output tokens:
Nemotron Cascade 2 30B A3B$0.00
gpt-oss-120B (high)$0.21

Speed Comparison

Output Speed (tokens/s) — higher is better
Nemotron Cascade 2 30B A3B
gpt-oss-120B (high)
276 tok/s
Time to First Token (seconds) — lower is better
Nemotron Cascade 2 30B A3B
gpt-oss-120B (high)
0.48s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
27.733.3
Coding Index
25.128.6
Math Index
93.4
GPQA Diamond
76.3%78.2%
MMLU-Pro
80.8%
LiveCodeBench
87.8%
AIME 2025
93.4%
MATH-500
Humanity's Last Exam
11.4%18.5%
SciCode
33.0%38.9%
IFBench
75.9%69.0%
TerminalBench
21.2%23.5%
Nemotron Cascade 2 30B A3B1 wins
10 winsgpt-oss-120B (high)

Frequently Asked Questions

Which is cheaper, Nemotron Cascade 2 30B A3B or gpt-oss-120B (high)?

Nemotron Cascade 2 30B A3B is cheaper overall. Its blended price (3:1 input/output ratio) is $0.00/M tokens vs $0.26/M for gpt-oss-120B (high).

Which model performs better on benchmarks?

gpt-oss-120B (high) wins 10 out of 12 benchmarks compared to 1 for Nemotron Cascade 2 30B A3B. 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 276 tok/s vs 0 tok/s. Nemotron Cascade 2 30B A3B also has lower time-to-first-token (0.00s vs 0.48s).

When should I use Nemotron Cascade 2 30B A3B vs gpt-oss-120B (high)?

Choose based on your priorities: Nemotron Cascade 2 30B A3B 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.