Compare/Mistral Small (Sep '24) vs GPT-4o mini

Mistral Small (Sep '24)vsGPT-4o mini

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

Mistral

Mistral Small (Sep '24)

Input
$0.2/M
Output
$0.6/M
Speed
155 tok/s
TTFT
0.54s
OpenAI

GPT-4o mini

Input
$0.15/M
Output
$0.6/M
Speed
66 tok/s
TTFT
0.70s

Winner by Category

Cheaper
GPT-4o mini
Faster (tok/s)
Mistral Small (Sep '24)
Lower Latency
Mistral Small (Sep '24)
Benchmarks (1-9)
GPT-4o mini

Pricing Comparison

MetricMistral Small (Sep '24)GPT-4o mini
Input ($/M tokens)$0.2$0.15
Output ($/M tokens)$0.6$0.6
Cost for 1M input + 100K output tokens:
Mistral Small (Sep '24)$0.26
GPT-4o mini$0.21

Speed Comparison

Output Speed (tokens/s) — higher is better
Mistral Small (Sep '24)
155 tok/s
GPT-4o mini
66 tok/s
Time to First Token (seconds) — lower is better
Mistral Small (Sep '24)
0.54s
GPT-4o mini
0.70s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
10.212.6
Coding Index
Math Index
14.7
GPQA Diamond
38.1%42.6%
MMLU-Pro
52.9%64.8%
LiveCodeBench
14.1%23.4%
AIME 2025
14.7%
MATH-500
56.3%78.9%
Humanity's Last Exam
4.3%4.0%
SciCode
15.6%22.9%
IFBench
31.0%
TerminalBench
Mistral Small (Sep '24)1 wins
9 winsGPT-4o mini

Frequently Asked Questions

Which is cheaper, Mistral Small (Sep '24) or GPT-4o mini?

GPT-4o mini is cheaper overall. Its blended price (3:1 input/output ratio) is $0.26/M tokens vs $0.30/M for Mistral Small (Sep '24).

Which model performs better on benchmarks?

GPT-4o mini wins 9 out of 12 benchmarks compared to 1 for Mistral Small (Sep '24). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mistral Small (Sep '24) generates tokens faster at 155 tok/s vs 66 tok/s. Mistral Small (Sep '24) also has lower time-to-first-token (0.54s vs 0.70s).

When should I use Mistral Small (Sep '24) vs GPT-4o mini?

Choose based on your priorities: GPT-4o mini for lower cost, GPT-4o mini for stronger benchmark performance, and Mistral Small (Sep '24) for faster generation. For latency-sensitive apps, check the TTFT comparison above.