Compare/DeepSeek V3.2 (Non-reasoning) vs Mistral Large 3

DeepSeek V3.2 (Non-reasoning)vsMistral Large 3

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

DeepSeek

DeepSeek V3.2 (Non-reasoning)

Input
$0.5/M
Output
$1.6/M
Speed
TTFT
Mistral

Mistral Large 3

Input
$0.5/M
Output
$1.5/M
Speed
55 tok/s
TTFT
0.60s

Winner by Category

Cheaper
Mistral Large 3
Faster (tok/s)
Mistral Large 3
Lower Latency
DeepSeek V3.2 (Non-reasoning)
Benchmarks (11-0)
DeepSeek V3.2 (Non-reasoning)

Pricing Comparison

MetricDeepSeek V3.2 (Non-reasoning)Mistral Large 3
Input ($/M tokens)$0.5$0.5
Output ($/M tokens)$1.6$1.5
Cost for 1M input + 100K output tokens:
DeepSeek V3.2 (Non-reasoning)$0.66
Mistral Large 3$0.65

Speed Comparison

Output Speed (tokens/s) — higher is better
DeepSeek V3.2 (Non-reasoning)
Mistral Large 3
55 tok/s
Time to First Token (seconds) — lower is better
DeepSeek V3.2 (Non-reasoning)
Mistral Large 3
0.60s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
32.122.8
Coding Index
34.622.7
Math Index
59.038.0
GPQA Diamond
75.1%68.0%
MMLU-Pro
83.7%80.7%
LiveCodeBench
59.3%46.5%
AIME 2025
59.0%38.0%
MATH-500
Humanity's Last Exam
10.5%4.1%
SciCode
38.7%36.2%
IFBench
49.0%36.2%
TerminalBench
32.6%15.9%
DeepSeek V3.2 (Non-reasoning)11 wins
0 winsMistral Large 3

Frequently Asked Questions

Which is cheaper, DeepSeek V3.2 (Non-reasoning) or Mistral Large 3?

Mistral Large 3 is cheaper overall. Its blended price (3:1 input/output ratio) is $0.75/M tokens vs $0.78/M for DeepSeek V3.2 (Non-reasoning).

Which model performs better on benchmarks?

DeepSeek V3.2 (Non-reasoning) wins 11 out of 12 benchmarks compared to 0 for Mistral Large 3. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mistral Large 3 generates tokens faster at 55 tok/s vs 0 tok/s. DeepSeek V3.2 (Non-reasoning) also has lower time-to-first-token (0.00s vs 0.60s).

When should I use DeepSeek V3.2 (Non-reasoning) vs Mistral Large 3?

Choose based on your priorities: Mistral Large 3 for lower cost, DeepSeek V3.2 (Non-reasoning) for stronger benchmark performance, and Mistral Large 3 for faster generation. For latency-sensitive apps, check the TTFT comparison above.