The AI arena is free today

Open Superagent

DeepSeek-V4-Flash-0423 vs MiMo-V2.5-Pro

DeepSeek-V4-Flash-0423 leads the LLM Stats Score 36.1 to 25.7. DeepSeek-V4-Flash-0423 is 4.8x cheaper per token.

DeepSeek · Xiaomi · Updated for 2026

Which is better?

DeepSeek-V4-Flash-0423 leads the overall LLM Stats Score 36.1 to 25.7, ranking #87 overall.

The models split the 6 individual benchmarks reported for both models evenly.

On price, DeepSeek-V4-Flash-0423 is roughly 4.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose DeepSeek-V4-Flash-0423

  • overall performance matters — it scores 36.1 and ranks #87 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • cost matters — it's about 4.8x cheaper per token

Choose MiMo-V2.5-Pro

  • your work emphasizes agents — it leads those capability indexes
  • you want the most recent training data — it shipped Apr 2026

At a glance

The differences that matter most.

Core performance indexes
36.1
#87
25.7
#159
37.0
#77
24.1
#165
26.6
#69
32.7
#41
15.7
#88
23.9
#61
Cost, coverage & limits
Benchmark wins
3 of 6
3 of 6
Input price
$0.09 / M
$0.43 / M
Output price
$0.18 / M
$0.87 / M
Context window
1,048,576
1,048,576

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
DeepSeek-V4-Flash-0423
MiMo-V2.5-Pro
36.8#34
25.4#111
15.4#90
23.1#38
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

19 reported for DeepSeek-V4-Flash-0423 · 31 for MiMo-V2.5-Pro

6 shared

DeepSeek-V4-Flash-0423 outperforms in 3 benchmarks (GPQA, Humanity's Last Exam, MMLU-Pro), while MiMo-V2.5-Pro is better at 3 benchmarks (SWE-Bench Pro, SWE-Bench Verified, Terminal-Bench 2.0).

Both models are evenly matched across the benchmarks.

Wed Sep 23 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

DeepSeek-V4-Flash-0423 costs less

For input processing, DeepSeek-V4-Flash-0423 ($0.09/1M tokens) is 4.8x cheaper than MiMo-V2.5-Pro ($0.43/1M tokens).

For output processing, DeepSeek-V4-Flash-0423 ($0.18/1M tokens) is 4.8x cheaper than MiMo-V2.5-Pro ($0.87/1M tokens).

In conclusion, MiMo-V2.5-Pro is more expensive than DeepSeek-V4-Flash-0423.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Sep 23 2026 • llm-stats.com
DeepSeek
DeepSeek-V4-Flash-0423
Input tokens$0.09
Output tokens$0.18
Best providerDeepinfra
Xiaomi
MiMo-V2.5-Pro
Input tokens$0.43
Output tokens$0.87
Best providerXiaomi
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

739.2B diff

MiMo-V2.5-Pro has 739.2B more parameters than DeepSeek-V4-Flash-0423, making it 260.3% larger.

DeepSeek
DeepSeek-V4-Flash-0423
284.0Bparameters
Xiaomi
MiMo-V2.5-Pro
1.0Tparameters
284.0B
DeepSeek-V4-Flash-0423
1023.2B
MiMo-V2.5-Pro

Context Window

Maximum input and output token capacity

Both models have the same input context window of 1,048,576 tokens. DeepSeek-V4-Flash-0423 can generate longer responses up to 1,048,576 tokens, while MiMo-V2.5-Pro is limited to 131,072 tokens.

DeepSeek
DeepSeek-V4-Flash-0423
Input1,048,576 tokens
Output1,048,576 tokens
Xiaomi
MiMo-V2.5-Pro
Input1,048,576 tokens
Output131,072 tokens
Wed Sep 23 2026 • llm-stats.com

License

Usage and distribution terms

Both models are licensed under MIT.

Both models share the same licensing terms, providing consistent usage rights.

DeepSeek-V4-Flash-0423

MIT

Open weights

MiMo-V2.5-Pro

MIT

Open weights

Release Timeline

When each model was launched

DeepSeek-V4-Flash-0423 was released on 2026-04-23, while MiMo-V2.5-Pro was released on 2026-04-27.

MiMo-V2.5-Pro is 0 month newer than DeepSeek-V4-Flash-0423.

DeepSeek-V4-Flash-0423

Apr 23, 2026

5 months ago

MiMo-V2.5-Pro

Apr 27, 2026

4 months ago

4d newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

DeepSeek-V4-Flash-0423 is available from DeepInfra, Novita. MiMo-V2.5-Pro is available from Xiaomi, DeepInfra, Novita.

DeepSeek-V4-Flash-0423

deepinfra logo
Deepinfra
Input Price:Input: $0.09/1MOutput Price:Output: $0.18/1M
novita logo
Novita
Input Price:Input: $0.14/1MOutput Price:Output: $0.28/1M

MiMo-V2.5-Pro

xiaomi logo
Xiaomi
Input Price:Input: $0.43/1MOutput Price:Output: $0.87/1M
deepinfra logo
Deepinfra
Input Price:Input: $1.00/1MOutput Price:Output: $3.00/1M
novita logo
Novita
Input Price:Input: $2.00/1MOutput Price:Output: $6.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against DeepSeek-V4-Flash-0423 and MiMo-V2.5-Pro side-by-side, then vote on the output you prefer.

DeepSeek-V4-Flash-0423
✓ Preferred
MiMo-V2.5-Pro
Open in Playground

FAQ

Common questions about DeepSeek-V4-Flash-0423 vs MiMo-V2.5-Pro.

Which is better, DeepSeek-V4-Flash-0423 or MiMo-V2.5-Pro?

DeepSeek-V4-Flash-0423 leads the LLM Stats Score 36.1 to 25.7. DeepSeek-V4-Flash-0423 is made by DeepSeek and MiMo-V2.5-Pro is made by Xiaomi. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DeepSeek-V4-Flash-0423 compare to MiMo-V2.5-Pro in benchmarks?

DeepSeek-V4-Flash-0423 scores CodeForces: 93.9%, HMMT Feb 26: 91.9%, LiveCodeBench: 88.4%, GPQA: 87.4%, MMLU-Pro: 86.4%. MiMo-V2.5-Pro scores FrontierSWE (Impl.): 100.0%, GSM8k: 99.6%, ARC-C: 97.2%, MMLU-Redux: 92.8%, C-Eval: 91.5%.

Is DeepSeek-V4-Flash-0423 cheaper than MiMo-V2.5-Pro?

DeepSeek-V4-Flash-0423 is 4.8x cheaper for input tokens. DeepSeek-V4-Flash-0423 costs $0.09/M input and $0.18/M output via deepinfra. MiMo-V2.5-Pro costs $0.43/M input and $0.87/M output via xiaomi.

What are the context window sizes for DeepSeek-V4-Flash-0423 and MiMo-V2.5-Pro?

DeepSeek-V4-Flash-0423 supports 1.0M tokens and MiMo-V2.5-Pro supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V4-Flash-0423 and MiMo-V2.5-Pro?

Key differences include LLM Stats Score (36.1 vs 25.7), input pricing ($0.09 vs $0.43/M). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V4-Flash-0423 and MiMo-V2.5-Pro?

DeepSeek-V4-Flash-0423 is developed by DeepSeek and MiMo-V2.5-Pro is developed by Xiaomi.