Compare/Gemini 3 Flash Preview (Reasoning) vs Mercury 2

Gemini 3 Flash Preview (Reasoning)vsMercury 2

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

Google

Gemini 3 Flash Preview (Reasoning)

Input
$0.5/M
Output
$3/M
Speed
180 tok/s
TTFT
6.33s
Inception

Mercury 2

Input
$0.25/M
Output
$0.75/M
Speed
907 tok/s
TTFT
3.76s

Winner by Category

Cheaper
Mercury 2
Faster (tok/s)
Mercury 2
Lower Latency
Mercury 2
Benchmarks (11-0)
Gemini 3 Flash Preview (Reasoning)

Pricing Comparison

MetricGemini 3 Flash Preview (Reasoning)Mercury 2
Input ($/M tokens)$0.5$0.25
Output ($/M tokens)$3$0.75
Cost for 1M input + 100K output tokens:
Gemini 3 Flash Preview (Reasoning)$0.80
Mercury 2$0.33

Speed Comparison

Output Speed (tokens/s) — higher is better
Gemini 3 Flash Preview (Reasoning)
180 tok/s
Mercury 2
907 tok/s
Time to First Token (seconds) — lower is better
Gemini 3 Flash Preview (Reasoning)
6.33s
Mercury 2
3.76s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
46.432.8
Coding Index
42.630.6
Math Index
97.0
GPQA Diamond
89.8%77.0%
MMLU-Pro
89.0%
LiveCodeBench
90.8%
AIME 2025
97.0%
MATH-500
Humanity's Last Exam
34.7%15.5%
SciCode
50.6%38.7%
IFBench
78.0%69.8%
TerminalBench
38.6%26.5%
Gemini 3 Flash Preview (Reasoning)11 wins
0 winsMercury 2

Frequently Asked Questions

Which is cheaper, Gemini 3 Flash Preview (Reasoning) or Mercury 2?

Mercury 2 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.38/M tokens vs $1.13/M for Gemini 3 Flash Preview (Reasoning).

Which model performs better on benchmarks?

Gemini 3 Flash Preview (Reasoning) wins 11 out of 12 benchmarks compared to 0 for Mercury 2. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mercury 2 generates tokens faster at 907 tok/s vs 180 tok/s. However, Mercury 2 has lower time-to-first-token (3.76s vs 6.33s).

When should I use Gemini 3 Flash Preview (Reasoning) vs Mercury 2?

Choose based on your priorities: Mercury 2 for lower cost, Gemini 3 Flash Preview (Reasoning) for stronger benchmark performance, and Mercury 2 for faster generation. For latency-sensitive apps, check the TTFT comparison above.