Compare/Mistral Small 3.2 vs Gemma 3 27B Instruct

Mistral Small 3.2vsGemma 3 27B Instruct

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

Mistral

Mistral Small 3.2

Input
$0.087/M
Output
$0.25/M
Speed
121 tok/s
TTFT
0.43s
Google

Gemma 3 27B Instruct

Input
$0.11/M
Output
$0.25/M
Speed
TTFT

Winner by Category

Cheaper
Mistral Small 3.2
Faster (tok/s)
Mistral Small 3.2
Lower Latency
Gemma 3 27B Instruct
Benchmarks (10-1)
Mistral Small 3.2

Pricing Comparison

MetricMistral Small 3.2Gemma 3 27B Instruct
Input ($/M tokens)$0.087$0.11
Output ($/M tokens)$0.25$0.25
Cost for 1M input + 100K output tokens:
Mistral Small 3.2$0.11
Gemma 3 27B Instruct$0.14

Speed Comparison

Output Speed (tokens/s) — higher is better
Mistral Small 3.2
121 tok/s
Gemma 3 27B Instruct
Time to First Token (seconds) — lower is better
Mistral Small 3.2
0.43s
Gemma 3 27B Instruct

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
15.110.3
Coding Index
13.39.6
Math Index
27.020.7
GPQA Diamond
50.5%42.8%
MMLU-Pro
68.1%66.9%
LiveCodeBench
27.5%13.7%
AIME 2025
27.0%20.7%
MATH-500
88.3%88.3%
Humanity's Last Exam
4.3%4.7%
SciCode
26.4%21.2%
IFBench
33.5%31.8%
TerminalBench
6.8%3.8%
Mistral Small 3.210 wins
1 winsGemma 3 27B Instruct

Frequently Asked Questions

Which is cheaper, Mistral Small 3.2 or Gemma 3 27B Instruct?

Mistral Small 3.2 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.13/M tokens vs $0.14/M for Gemma 3 27B Instruct.

Which model performs better on benchmarks?

Mistral Small 3.2 wins 10 out of 12 benchmarks compared to 1 for Gemma 3 27B Instruct. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mistral Small 3.2 generates tokens faster at 121 tok/s vs 0 tok/s. However, Gemma 3 27B Instruct has lower time-to-first-token (0.00s vs 0.43s).

When should I use Mistral Small 3.2 vs Gemma 3 27B Instruct?

Choose based on your priorities: Mistral Small 3.2 for lower cost, Mistral Small 3.2 for stronger benchmark performance, and Mistral Small 3.2 for faster generation. For latency-sensitive apps, check the TTFT comparison above.