Compare/Qwen3 32B (Non-reasoning) vs Mistral Small 4 (Reasoning)

Qwen3 32B (Non-reasoning)vsMistral Small 4 (Reasoning)

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

Alibaba

Qwen3 32B (Non-reasoning)

Input
$0.15/M
Output
$0.59/M
Speed
103 tok/s
TTFT
1.09s
Mistral

Mistral Small 4 (Reasoning)

Input
$0.15/M
Output
$0.6/M
Speed
163 tok/s
TTFT
0.57s

Winner by Category

Cheaper
Qwen3 32B (Non-reasoning)
Faster (tok/s)
Mistral Small 4 (Reasoning)
Lower Latency
Mistral Small 4 (Reasoning)
Benchmarks (5-7)
Mistral Small 4 (Reasoning)

Pricing Comparison

MetricQwen3 32B (Non-reasoning)Mistral Small 4 (Reasoning)
Input ($/M tokens)$0.15$0.15
Output ($/M tokens)$0.59$0.6
Cost for 1M input + 100K output tokens:
Qwen3 32B (Non-reasoning)$0.21
Mistral Small 4 (Reasoning)$0.21

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3 32B (Non-reasoning)
103 tok/s
Mistral Small 4 (Reasoning)
163 tok/s
Time to First Token (seconds) — lower is better
Qwen3 32B (Non-reasoning)
1.09s
Mistral Small 4 (Reasoning)
0.57s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
14.527.8
Coding Index
24.3
Math Index
19.7
GPQA Diamond
53.5%76.9%
MMLU-Pro
72.7%
LiveCodeBench
28.8%
AIME 2025
19.7%
MATH-500
86.9%
Humanity's Last Exam
4.3%9.5%
SciCode
28.0%38.0%
IFBench
31.5%48.2%
TerminalBench
17.4%
Qwen3 32B (Non-reasoning)5 wins
7 winsMistral Small 4 (Reasoning)

Frequently Asked Questions

Which is cheaper, Qwen3 32B (Non-reasoning) or Mistral Small 4 (Reasoning)?

Qwen3 32B (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.26/M tokens vs $0.26/M for Mistral Small 4 (Reasoning).

Which model performs better on benchmarks?

Mistral Small 4 (Reasoning) wins 7 out of 12 benchmarks compared to 5 for Qwen3 32B (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mistral Small 4 (Reasoning) generates tokens faster at 163 tok/s vs 103 tok/s. However, Mistral Small 4 (Reasoning) has lower time-to-first-token (0.57s vs 1.09s).

When should I use Qwen3 32B (Non-reasoning) vs Mistral Small 4 (Reasoning)?

Choose based on your priorities: Qwen3 32B (Non-reasoning) for lower cost, Mistral Small 4 (Reasoning) for stronger benchmark performance, and Mistral Small 4 (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.