Compare/GPT-5 (minimal) vs Nova 2.0 Pro Preview (low)

GPT-5 (minimal)vsNova 2.0 Pro Preview (low)

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

OpenAI

GPT-5 (minimal)

Input
$1.25/M
Output
$10/M
Speed
82 tok/s
TTFT
0.89s
Amazon

Nova 2.0 Pro Preview (low)

Input
$1.25/M
Output
$10/M
Speed
148 tok/s
TTFT
5.85s

Winner by Category

Cheaper
Tie
Faster (tok/s)
Nova 2.0 Pro Preview (low)
Lower Latency
GPT-5 (minimal)
Benchmarks (5-7)
Nova 2.0 Pro Preview (low)

Pricing Comparison

MetricGPT-5 (minimal)Nova 2.0 Pro Preview (low)
Input ($/M tokens)$1.25$1.25
Output ($/M tokens)$10$10
Cost for 1M input + 100K output tokens:
GPT-5 (minimal)$2.25
Nova 2.0 Pro Preview (low)$2.25

Speed Comparison

Output Speed (tokens/s) — higher is better
GPT-5 (minimal)
82 tok/s
Nova 2.0 Pro Preview (low)
148 tok/s
Time to First Token (seconds) — lower is better
GPT-5 (minimal)
0.89s
Nova 2.0 Pro Preview (low)
5.85s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
23.931.9
Coding Index
25.124.5
Math Index
31.763.3
GPQA Diamond
67.3%75.1%
MMLU-Pro
80.6%82.2%
LiveCodeBench
55.8%63.8%
AIME 2025
31.7%63.3%
MATH-500
86.1%
Humanity's Last Exam
5.4%5.2%
SciCode
38.8%38.7%
IFBench
45.6%79.6%
TerminalBench
18.2%17.4%
GPT-5 (minimal)5 wins
7 winsNova 2.0 Pro Preview (low)

Frequently Asked Questions

Which is cheaper, GPT-5 (minimal) or Nova 2.0 Pro Preview (low)?

Both models have similar pricing. Check the detailed breakdown above for input vs output token costs.

Which model performs better on benchmarks?

Nova 2.0 Pro Preview (low) wins 7 out of 12 benchmarks compared to 5 for GPT-5 (minimal). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Nova 2.0 Pro Preview (low) generates tokens faster at 148 tok/s vs 82 tok/s. GPT-5 (minimal) also has lower time-to-first-token (0.89s vs 5.85s).

When should I use GPT-5 (minimal) vs Nova 2.0 Pro Preview (low)?

Choose based on your priorities: both are similarly priced, Nova 2.0 Pro Preview (low) for stronger benchmark performance, and Nova 2.0 Pro Preview (low) for faster generation. For latency-sensitive apps, check the TTFT comparison above.