Compare/GPT-4o mini vs Mistral Small 4 (Non-reasoning)

GPT-4o minivsMistral Small 4 (Non-reasoning)

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

OpenAI

GPT-4o mini

Input
$0.15/M
Output
$0.6/M
Speed
49 tok/s
TTFT
0.51s
Mistral

Mistral Small 4 (Non-reasoning)

Input
$0.15/M
Output
$0.6/M
Speed
152 tok/s
TTFT
0.53s

Winner by Category

Cheaper
Tie
Faster (tok/s)
Mistral Small 4 (Non-reasoning)
Lower Latency
GPT-4o mini
Benchmarks (6-6)
Tie

Pricing Comparison

MetricGPT-4o miniMistral Small 4 (Non-reasoning)
Input ($/M tokens)$0.15$0.15
Output ($/M tokens)$0.6$0.6
Cost for 1M input + 100K output tokens:
GPT-4o mini$0.21
Mistral Small 4 (Non-reasoning)$0.21

Speed Comparison

Output Speed (tokens/s) — higher is better
GPT-4o mini
49 tok/s
Mistral Small 4 (Non-reasoning)
152 tok/s
Time to First Token (seconds) — lower is better
GPT-4o mini
0.51s
Mistral Small 4 (Non-reasoning)
0.53s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
12.618.6
Coding Index
16.4
Math Index
14.7
GPQA Diamond
42.6%57.1%
MMLU-Pro
64.8%
LiveCodeBench
23.4%
AIME 2025
14.7%
MATH-500
78.9%
Humanity's Last Exam
4.0%3.7%
SciCode
22.9%28.1%
IFBench
31.0%32.8%
TerminalBench
10.6%
GPT-4o mini6 wins
6 winsMistral Small 4 (Non-reasoning)

Frequently Asked Questions

Which is cheaper, GPT-4o mini or Mistral Small 4 (Non-reasoning)?

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

Which model performs better on benchmarks?

It's a tie — both models win 6 benchmarks each across 12 evaluated categories. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mistral Small 4 (Non-reasoning) generates tokens faster at 152 tok/s vs 49 tok/s. GPT-4o mini also has lower time-to-first-token (0.51s vs 0.53s).

When should I use GPT-4o mini vs Mistral Small 4 (Non-reasoning)?

Choose based on your priorities: both are similarly priced, both perform similarly on benchmarks, and Mistral Small 4 (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.