Compare/Ministral 3 14B vs Apertus 8B Instruct

Ministral 3 14BvsApertus 8B Instruct

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

Mistral

Ministral 3 14B

Input
$0.2/M
Output
$0.2/M
Speed
125 tok/s
TTFT
0.28s
Swiss AI Initiative

Apertus 8B Instruct

Input
$0.1/M
Output
$0.2/M
Speed
140 tok/s
TTFT
1.77s

Winner by Category

Cheaper
Apertus 8B Instruct
Faster (tok/s)
Apertus 8B Instruct
Lower Latency
Ministral 3 14B
Benchmarks (10-1)
Ministral 3 14B

Pricing Comparison

MetricMinistral 3 14BApertus 8B Instruct
Input ($/M tokens)$0.2$0.1
Output ($/M tokens)$0.2$0.2
Cost for 1M input + 100K output tokens:
Ministral 3 14B$0.22
Apertus 8B Instruct$0.12

Speed Comparison

Output Speed (tokens/s) — higher is better
Ministral 3 14B
125 tok/s
Apertus 8B Instruct
140 tok/s
Time to First Token (seconds) — lower is better
Ministral 3 14B
0.28s
Apertus 8B Instruct
1.77s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
16.05.9
Coding Index
10.91.4
Math Index
30.0
GPQA Diamond
57.2%25.6%
MMLU-Pro
69.3%
LiveCodeBench
35.1%
AIME 2025
30.0%
MATH-500
Humanity's Last Exam
4.6%5.0%
SciCode
23.6%4.1%
IFBench
32.0%22.4%
TerminalBench
4.5%0.0%
Ministral 3 14B10 wins
1 winsApertus 8B Instruct

Frequently Asked Questions

Which is cheaper, Ministral 3 14B or Apertus 8B Instruct?

Apertus 8B Instruct is cheaper overall. Its blended price (3:1 input/output ratio) is $0.13/M tokens vs $0.20/M for Ministral 3 14B.

Which model performs better on benchmarks?

Ministral 3 14B wins 10 out of 12 benchmarks compared to 1 for Apertus 8B Instruct. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Apertus 8B Instruct generates tokens faster at 140 tok/s vs 125 tok/s. Ministral 3 14B also has lower time-to-first-token (0.28s vs 1.77s).

When should I use Ministral 3 14B vs Apertus 8B Instruct?

Choose based on your priorities: Apertus 8B Instruct for lower cost, Ministral 3 14B for stronger benchmark performance, and Apertus 8B Instruct for faster generation. For latency-sensitive apps, check the TTFT comparison above.