Compare/Qwen3 32B (Reasoning) vs Mistral Medium

Qwen3 32B (Reasoning)vsMistral Medium

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

Alibaba

Qwen3 32B (Reasoning)

Input
$0.7/M
Output
$8.4/M
Speed
103 tok/s
TTFT
0.97s
Mistral

Mistral Medium

Input
$2.75/M
Output
$8.1/M
Speed
73 tok/s
TTFT
0.40s

Winner by Category

Cheaper
Qwen3 32B (Reasoning)
Faster (tok/s)
Qwen3 32B (Reasoning)
Lower Latency
Mistral Medium
Benchmarks (12-0)
Qwen3 32B (Reasoning)

Pricing Comparison

MetricQwen3 32B (Reasoning)Mistral Medium
Input ($/M tokens)$0.7$2.75
Output ($/M tokens)$8.4$8.1
Cost for 1M input + 100K output tokens:
Qwen3 32B (Reasoning)$1.54
Mistral Medium$3.56

Speed Comparison

Output Speed (tokens/s) — higher is better
Qwen3 32B (Reasoning)
103 tok/s
Mistral Medium
73 tok/s
Time to First Token (seconds) — lower is better
Qwen3 32B (Reasoning)
0.97s
Mistral Medium
0.40s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
16.59.0
Coding Index
13.8
Math Index
73.0
GPQA Diamond
66.8%34.9%
MMLU-Pro
79.8%49.1%
LiveCodeBench
54.6%9.9%
AIME 2025
73.0%
MATH-500
96.1%40.5%
Humanity's Last Exam
8.3%3.4%
SciCode
35.4%11.8%
IFBench
36.3%
TerminalBench
3.0%
Qwen3 32B (Reasoning)12 wins
0 winsMistral Medium

Frequently Asked Questions

Which is cheaper, Qwen3 32B (Reasoning) or Mistral Medium?

Qwen3 32B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $2.63/M tokens vs $4.09/M for Mistral Medium.

Which model performs better on benchmarks?

Qwen3 32B (Reasoning) wins 12 out of 12 benchmarks compared to 0 for Mistral Medium. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Qwen3 32B (Reasoning) generates tokens faster at 103 tok/s vs 73 tok/s. However, Mistral Medium has lower time-to-first-token (0.40s vs 0.97s).

When should I use Qwen3 32B (Reasoning) vs Mistral Medium?

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