Compare/Nova 2.0 Lite (high) vs gpt-oss-120B (high)

Nova 2.0 Lite (high)vsgpt-oss-120B (high)

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

Amazon

Nova 2.0 Lite (high)

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

gpt-oss-120B (high)

Input
$0.15/M
Output
$0.6/M
Speed
237 tok/s
TTFT
0.51s

Winner by Category

Cheaper
Nova 2.0 Lite (high)
Faster (tok/s)
gpt-oss-120B (high)
Lower Latency
Nova 2.0 Lite (high)
Benchmarks (6-5)
Nova 2.0 Lite (high)

Pricing Comparison

MetricNova 2.0 Lite (high)gpt-oss-120B (high)
Input ($/M tokens)$0$0.15
Output ($/M tokens)$0$0.6
Cost for 1M input + 100K output tokens:
Nova 2.0 Lite (high)$0.00
gpt-oss-120B (high)$0.21

Speed Comparison

Output Speed (tokens/s) — higher is better
Nova 2.0 Lite (high)
gpt-oss-120B (high)
237 tok/s
Time to First Token (seconds) — lower is better
Nova 2.0 Lite (high)
gpt-oss-120B (high)
0.51s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
34.533.3
Coding Index
23.428.6
Math Index
94.393.4
GPQA Diamond
81.1%78.2%
MMLU-Pro
81.8%80.8%
LiveCodeBench
71.1%87.8%
AIME 2025
94.3%93.4%
MATH-500
Humanity's Last Exam
10.9%18.5%
SciCode
36.9%38.9%
IFBench
70.7%69.0%
TerminalBench
16.7%23.5%
Nova 2.0 Lite (high)6 wins
5 winsgpt-oss-120B (high)

Frequently Asked Questions

Which is cheaper, Nova 2.0 Lite (high) or gpt-oss-120B (high)?

Nova 2.0 Lite (high) 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?

Nova 2.0 Lite (high) wins 6 out of 12 benchmarks compared to 5 for gpt-oss-120B (high). 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 237 tok/s vs 0 tok/s. Nova 2.0 Lite (high) also has lower time-to-first-token (0.00s vs 0.51s).

When should I use Nova 2.0 Lite (high) vs gpt-oss-120B (high)?

Choose based on your priorities: Nova 2.0 Lite (high) for lower cost, Nova 2.0 Lite (high) for stronger benchmark performance, and gpt-oss-120B (high) for faster generation. For latency-sensitive apps, check the TTFT comparison above.