Compare/Mistral Large 3 vs DeepSeek V3.1 Terminus (Non-reasoning)

Mistral Large 3vsDeepSeek V3.1 Terminus (Non-reasoning)

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

Mistral

Mistral Large 3

Input
$0.5/M
Output
$1.5/M
Speed
57 tok/s
TTFT
0.53s
DeepSeek

DeepSeek V3.1 Terminus (Non-reasoning)

Input
$0.335/M
Output
$1.5/M
Speed
TTFT

Winner by Category

Cheaper
DeepSeek V3.1 Terminus (Non-reasoning)
Faster (tok/s)
Mistral Large 3
Lower Latency
DeepSeek V3.1 Terminus (Non-reasoning)
Benchmarks (1-10)
DeepSeek V3.1 Terminus (Non-reasoning)

Pricing Comparison

MetricMistral Large 3DeepSeek V3.1 Terminus (Non-reasoning)
Input ($/M tokens)$0.5$0.335
Output ($/M tokens)$1.5$1.5
Cost for 1M input + 100K output tokens:
Mistral Large 3$0.65
DeepSeek V3.1 Terminus (Non-reasoning)$0.49

Speed Comparison

Output Speed (tokens/s) — higher is better
Mistral Large 3
57 tok/s
DeepSeek V3.1 Terminus (Non-reasoning)
Time to First Token (seconds) — lower is better
Mistral Large 3
0.53s
DeepSeek V3.1 Terminus (Non-reasoning)

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
22.828.5
Coding Index
22.731.9
Math Index
38.053.7
GPQA Diamond
68.0%75.1%
MMLU-Pro
80.7%83.6%
LiveCodeBench
46.5%52.9%
AIME 2025
38.0%53.7%
MATH-500
Humanity's Last Exam
4.1%8.4%
SciCode
36.2%32.1%
IFBench
36.2%41.2%
TerminalBench
15.9%31.8%
Mistral Large 31 wins
10 winsDeepSeek V3.1 Terminus (Non-reasoning)

Frequently Asked Questions

Which is cheaper, Mistral Large 3 or DeepSeek V3.1 Terminus (Non-reasoning)?

DeepSeek V3.1 Terminus (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.63/M tokens vs $0.75/M for Mistral Large 3.

Which model performs better on benchmarks?

DeepSeek V3.1 Terminus (Non-reasoning) wins 10 out of 12 benchmarks compared to 1 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 57 tok/s vs 0 tok/s. However, DeepSeek V3.1 Terminus (Non-reasoning) has lower time-to-first-token (0.00s vs 0.53s).

When should I use Mistral Large 3 vs DeepSeek V3.1 Terminus (Non-reasoning)?

Choose based on your priorities: DeepSeek V3.1 Terminus (Non-reasoning) for lower cost, DeepSeek V3.1 Terminus (Non-reasoning) for stronger benchmark performance, and Mistral Large 3 for faster generation. For latency-sensitive apps, check the TTFT comparison above.