Compare/DeepSeek V3 (Dec '24) vs MiMo-V2.5-Pro

DeepSeek V3 (Dec '24)vsMiMo-V2.5-Pro

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

DeepSeek

DeepSeek V3 (Dec '24)

Input
$0.4/M
Output
$0.89/M
Speed
TTFT
Xiaomi

MiMo-V2.5-Pro

Input
$0.435/M
Output
$0.87/M
Speed
48 tok/s
TTFT
1.92s

Winner by Category

Cheaper
DeepSeek V3 (Dec '24)
Faster (tok/s)
MiMo-V2.5-Pro
Lower Latency
DeepSeek V3 (Dec '24)
Benchmarks (5-7)
MiMo-V2.5-Pro

Pricing Comparison

MetricDeepSeek V3 (Dec '24)MiMo-V2.5-Pro
Input ($/M tokens)$0.4$0.435
Output ($/M tokens)$0.89$0.87
Cost for 1M input + 100K output tokens:
DeepSeek V3 (Dec '24)$0.49
MiMo-V2.5-Pro$0.52

Speed Comparison

Output Speed (tokens/s) — higher is better
DeepSeek V3 (Dec '24)
MiMo-V2.5-Pro
48 tok/s
Time to First Token (seconds) — lower is better
DeepSeek V3 (Dec '24)
MiMo-V2.5-Pro
1.92s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
14.242.2
Coding Index
23.060.2
Math Index
26.0
GPQA Diamond
55.7%86.6%
MMLU-Pro
75.2%
LiveCodeBench
35.9%
AIME 2025
26.0%
MATH-500
88.7%
Humanity's Last Exam
3.6%33.8%
SciCode
35.4%50.2%
IFBench
34.8%79.9%
TerminalBench
6.8%43.2%
DeepSeek V3 (Dec '24)5 wins
7 winsMiMo-V2.5-Pro

Frequently Asked Questions

Which is cheaper, DeepSeek V3 (Dec '24) or MiMo-V2.5-Pro?

DeepSeek V3 (Dec '24) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.52/M tokens vs $0.54/M for MiMo-V2.5-Pro.

Which model performs better on benchmarks?

MiMo-V2.5-Pro wins 7 out of 12 benchmarks compared to 5 for DeepSeek V3 (Dec '24). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

MiMo-V2.5-Pro generates tokens faster at 48 tok/s vs 0 tok/s. DeepSeek V3 (Dec '24) also has lower time-to-first-token (0.00s vs 1.92s).

When should I use DeepSeek V3 (Dec '24) vs MiMo-V2.5-Pro?

Choose based on your priorities: DeepSeek V3 (Dec '24) for lower cost, MiMo-V2.5-Pro for stronger benchmark performance, and MiMo-V2.5-Pro for faster generation. For latency-sensitive apps, check the TTFT comparison above.