Compare/Gemini 3 Pro Preview (high) vs Nova 2.0 Pro Preview (Non-reasoning)

Gemini 3 Pro Preview (high)vsNova 2.0 Pro Preview (Non-reasoning)

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

Google

Gemini 3 Pro Preview (high)

Input
$2/M
Output
$12/M
Speed
117 tok/s
TTFT
39.61s
Amazon

Nova 2.0 Pro Preview (Non-reasoning)

Input
$1.25/M
Output
$10/M
Speed
163 tok/s
TTFT
0.48s

Winner by Category

Cheaper
Nova 2.0 Pro Preview (Non-reasoning)
Faster (tok/s)
Nova 2.0 Pro Preview (Non-reasoning)
Lower Latency
Nova 2.0 Pro Preview (Non-reasoning)
Benchmarks (11-0)
Gemini 3 Pro Preview (high)

Pricing Comparison

MetricGemini 3 Pro Preview (high)Nova 2.0 Pro Preview (Non-reasoning)
Input ($/M tokens)$2$1.25
Output ($/M tokens)$12$10
Cost for 1M input + 100K output tokens:
Gemini 3 Pro Preview (high)$3.20
Nova 2.0 Pro Preview (Non-reasoning)$2.25

Speed Comparison

Output Speed (tokens/s) — higher is better
Gemini 3 Pro Preview (high)
117 tok/s
Nova 2.0 Pro Preview (Non-reasoning)
163 tok/s
Time to First Token (seconds) — lower is better
Gemini 3 Pro Preview (high)
39.61s
Nova 2.0 Pro Preview (Non-reasoning)
0.48s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
48.423.1
Coding Index
46.520.5
Math Index
95.730.7
GPQA Diamond
90.8%63.6%
MMLU-Pro
89.8%77.2%
LiveCodeBench
91.7%47.3%
AIME 2025
95.7%30.7%
MATH-500
Humanity's Last Exam
37.2%4.0%
SciCode
56.1%28.1%
IFBench
70.4%52.0%
TerminalBench
41.7%16.7%
Gemini 3 Pro Preview (high)11 wins
0 winsNova 2.0 Pro Preview (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Gemini 3 Pro Preview (high) or Nova 2.0 Pro Preview (Non-reasoning)?

Nova 2.0 Pro Preview (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $3.44/M tokens vs $4.50/M for Gemini 3 Pro Preview (high).

Which model performs better on benchmarks?

Gemini 3 Pro Preview (high) wins 11 out of 12 benchmarks compared to 0 for Nova 2.0 Pro Preview (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Nova 2.0 Pro Preview (Non-reasoning) generates tokens faster at 163 tok/s vs 117 tok/s. However, Nova 2.0 Pro Preview (Non-reasoning) has lower time-to-first-token (0.48s vs 39.61s).

When should I use Gemini 3 Pro Preview (high) vs Nova 2.0 Pro Preview (Non-reasoning)?

Choose based on your priorities: Nova 2.0 Pro Preview (Non-reasoning) for lower cost, Gemini 3 Pro Preview (high) for stronger benchmark performance, and Nova 2.0 Pro Preview (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.