Compare/Devstral Small (Jul '25) vs Gemma 4 12B (Reasoning)

Devstral Small (Jul '25)vsGemma 4 12B (Reasoning)

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

Mistral

Devstral Small (Jul '25)

Input
$0.1/M
Output
$0.3/M
Speed
48 tok/s
TTFT
0.57s
Google

Gemma 4 12B (Reasoning)

Input
$0.1/M
Output
$0.3/M
Speed
143 tok/s
TTFT
1.33s

Winner by Category

Cheaper
Tie
Faster (tok/s)
Gemma 4 12B (Reasoning)
Lower Latency
Devstral Small (Jul '25)
Benchmarks (5-6)
Gemma 4 12B (Reasoning)

Pricing Comparison

MetricDevstral Small (Jul '25)Gemma 4 12B (Reasoning)
Input ($/M tokens)$0.1$0.1
Output ($/M tokens)$0.3$0.3
Cost for 1M input + 100K output tokens:
Devstral Small (Jul '25)$0.13
Gemma 4 12B (Reasoning)$0.13

Speed Comparison

Output Speed (tokens/s) — higher is better
Devstral Small (Jul '25)
48 tok/s
Gemma 4 12B (Reasoning)
143 tok/s
Time to First Token (seconds) — lower is better
Devstral Small (Jul '25)
0.57s
Gemma 4 12B (Reasoning)
1.33s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
9.322.0
Coding Index
Math Index
29.3
GPQA Diamond
41.4%75.3%
MMLU-Pro
62.2%
LiveCodeBench
25.4%
AIME 2025
29.3%
MATH-500
63.5%
Humanity's Last Exam
3.7%14.8%
SciCode
24.3%38.2%
IFBench
34.6%73.5%
TerminalBench
6.1%18.2%
Devstral Small (Jul '25)5 wins
6 winsGemma 4 12B (Reasoning)

Frequently Asked Questions

Which is cheaper, Devstral Small (Jul '25) or Gemma 4 12B (Reasoning)?

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

Which model performs better on benchmarks?

Gemma 4 12B (Reasoning) wins 6 out of 12 benchmarks compared to 5 for Devstral Small (Jul '25). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Gemma 4 12B (Reasoning) generates tokens faster at 143 tok/s vs 48 tok/s. Devstral Small (Jul '25) also has lower time-to-first-token (0.57s vs 1.33s).

When should I use Devstral Small (Jul '25) vs Gemma 4 12B (Reasoning)?

Choose based on your priorities: both are similarly priced, Gemma 4 12B (Reasoning) for stronger benchmark performance, and Gemma 4 12B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.