Compare/GPT-5 mini (medium) vs Mistral Medium 3

GPT-5 mini (medium)vsMistral Medium 3

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

OpenAI

GPT-5 mini (medium)

Input
$0.25/M
Output
$2/M
Speed
72 tok/s
TTFT
16.59s
Mistral

Mistral Medium 3

Input
$0.4/M
Output
$2/M
Speed
52 tok/s
TTFT
0.37s

Winner by Category

Cheaper
GPT-5 mini (medium)
Faster (tok/s)
GPT-5 mini (medium)
Lower Latency
Mistral Medium 3
Benchmarks (11-1)
GPT-5 mini (medium)

Pricing Comparison

MetricGPT-5 mini (medium)Mistral Medium 3
Input ($/M tokens)$0.25$0.4
Output ($/M tokens)$2$2
Cost for 1M input + 100K output tokens:
GPT-5 mini (medium)$0.45
Mistral Medium 3$0.60

Speed Comparison

Output Speed (tokens/s) — higher is better
GPT-5 mini (medium)
72 tok/s
Mistral Medium 3
52 tok/s
Time to First Token (seconds) — lower is better
GPT-5 mini (medium)
16.59s
Mistral Medium 3
0.37s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
38.918.8
Coding Index
32.913.6
Math Index
85.030.3
GPQA Diamond
80.3%57.8%
MMLU-Pro
82.8%76.0%
LiveCodeBench
69.2%40.0%
AIME 2025
85.0%30.3%
MATH-500
90.7%
Humanity's Last Exam
14.6%4.3%
SciCode
41.0%33.1%
IFBench
71.2%39.3%
TerminalBench
28.8%3.8%
GPT-5 mini (medium)11 wins
1 winsMistral Medium 3

Frequently Asked Questions

Which is cheaper, GPT-5 mini (medium) or Mistral Medium 3?

GPT-5 mini (medium) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.69/M tokens vs $0.80/M for Mistral Medium 3.

Which model performs better on benchmarks?

GPT-5 mini (medium) wins 11 out of 12 benchmarks compared to 1 for Mistral Medium 3. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GPT-5 mini (medium) generates tokens faster at 72 tok/s vs 52 tok/s. However, Mistral Medium 3 has lower time-to-first-token (0.37s vs 16.59s).

When should I use GPT-5 mini (medium) vs Mistral Medium 3?

Choose based on your priorities: GPT-5 mini (medium) for lower cost, GPT-5 mini (medium) for stronger benchmark performance, and GPT-5 mini (medium) for faster generation. For latency-sensitive apps, check the TTFT comparison above.