DeepSeek-V4-Flash-0423 vs MiMo-V2-Pro
DeepSeek-V4-Flash-0423 and MiMo-V2-Pro are closely matched at 36.0 and 35.6 on the LLM Stats Score. DeepSeek-V4-Flash-0423 is 13.3x cheaper per token.
DeepSeek · Xiaomi · Updated for 2026
Which is better?
DeepSeek-V4-Flash-0423 and MiMo-V2-Pro are closely matched on the overall LLM Stats Score at 36.0 and 35.6.
In the 3 individual benchmarks reported for both models, MiMo-V2-Pro wins 2; this is a narrower head-to-head signal than the composite indexes.
On price, DeepSeek-V4-Flash-0423 is roughly 13.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
DeepSeek-V4-Flash-0423 also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose DeepSeek-V4-Flash-0423
- cost matters — it's about 13.3x cheaper per token
- you process long inputs — it offers a 1,048,576 token context window
- you want the most recent training data — it shipped Apr 2026
- you need open weights you can self-host or fine-tune
Choose MiMo-V2-Pro
- you value its reported benchmark strengths — it wins 2 of 3 exact shared results
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
19 reported for DeepSeek-V4-Flash-0423 · 7 for MiMo-V2-Pro
DeepSeek-V4-Flash-0423 outperforms in 1 benchmarks (SWE-Bench Verified), while MiMo-V2-Pro is better at 2 benchmarks (SWE-bench Multilingual, Terminal-Bench 2.0).
MiMo-V2-Pro shows notably better performance in the majority of benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, DeepSeek-V4-Flash-0423 ($0.09/1M tokens) is 11.1x cheaper than MiMo-V2-Pro ($1.00/1M tokens).
For output processing, DeepSeek-V4-Flash-0423 ($0.18/1M tokens) is 16.7x cheaper than MiMo-V2-Pro ($3.00/1M tokens).
In conclusion, MiMo-V2-Pro is more expensive than DeepSeek-V4-Flash-0423.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
MiMo-V2-Pro has 716.0B more parameters than DeepSeek-V4-Flash-0423, making it 252.1% larger.
Context Window
Maximum input and output token capacity
DeepSeek-V4-Flash-0423 accepts 1,048,576 input tokens compared to MiMo-V2-Pro's 1,000,000 tokens. DeepSeek-V4-Flash-0423 can generate longer responses up to 1,048,576 tokens, while MiMo-V2-Pro is limited to 16,384 tokens.
License
Usage and distribution terms
DeepSeek-V4-Flash-0423 is licensed under MIT, while MiMo-V2-Pro uses a proprietary license.
License differences may affect how you can use these models in commercial or open-source projects.
MIT
Open weights
Proprietary
Closed source
Release Timeline
When each model was launched
DeepSeek-V4-Flash-0423 was released on 2026-04-23, while MiMo-V2-Pro was released on 2026-03-18.
DeepSeek-V4-Flash-0423 is 1 month newer than MiMo-V2-Pro.
Apr 23, 2026
5 months ago
1mo newerMar 18, 2026
6 months ago
Knowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
DeepSeek-V4-Flash-0423 is available from DeepInfra, Novita. MiMo-V2-Pro is available from Xiaomi.
DeepSeek-V4-Flash-0423
MiMo-V2-Pro
Outputs Comparison
Judge for yourself.
Run your own prompts against DeepSeek-V4-Flash-0423 and MiMo-V2-Pro side-by-side, then vote on the output you prefer.
FAQ
Common questions about DeepSeek-V4-Flash-0423 vs MiMo-V2-Pro.