Model Comparison

Kimi K3 vs MiMo-V2.5Which is better in 2026?

Kimi K3 significantly outperforms across most benchmarks. MiMo-V2.5 is 28.6x cheaper per token.

Verdict: Kimi K3 vs MiMo-V2.5 — which is better?

Kimi K3 (by Moonshot AI) and MiMo-V2.5 (by Xiaomi) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Kimi K3 outperforms in 3 benchmarks (CharXiv-R, MMMU-Pro, OmniDocBench), while MiMo-V2.5 is better at 0 benchmarks. Kimi K3 significantly outperforms across most benchmarks.

On price, MiMo-V2.5 is roughly 28.6x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Choose Kimi K3 if…

  • you want the strongest raw capability — it leads on 3 of 3 shared benchmarks
  • you want the most recent training data — it shipped Jul 2026

Choose MiMo-V2.5 if…

  • cost matters — it's about 28.6x cheaper per token
  • you need open weights you can self-host or fine-tune

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

Kimi K3 outperforms in 3 benchmarks (CharXiv-R, MMMU-Pro, OmniDocBench), while MiMo-V2.5 is better at 0 benchmarks.

Kimi K3 significantly outperforms across most benchmarks.

Fri Jul 17 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

MiMo-V2.5 costs less

For input processing, Kimi K3 ($3.00/1M tokens) is 17.9x more expensive than MiMo-V2.5 ($0.17/1M tokens).

For output processing, Kimi K3 ($15.00/1M tokens) is 44.6x more expensive than MiMo-V2.5 ($0.34/1M tokens).

In conclusion, Kimi K3 is more expensive than MiMo-V2.5.*

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

Lowest available price from all providers
Fri Jul 17 2026 • llm-stats.com
Moonshot AI
Kimi K3
Input tokens$3.00
Output tokens$15.00
Best providerUnknown Organization
Xiaomi
MiMo-V2.5
Input tokens$0.17
Output tokens$0.34
Best providerNovita
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

2489.2B diff

Kimi K3 has 2489.2B more parameters than MiMo-V2.5, making it 801.0% larger.

Moonshot AI
Kimi K3
2.8Tparameters
Xiaomi
MiMo-V2.5
310.8Bparameters
2800.0B
Kimi K3
310.8B
MiMo-V2.5

Context Window

Maximum input and output token capacity

Both models have the same input context window of 1,048,576 tokens. Kimi K3 can generate longer responses up to 1,048,576 tokens, while MiMo-V2.5 is limited to 131,072 tokens.

Moonshot AI
Kimi K3
Input1,048,576 tokens
Output1,048,576 tokens
Xiaomi
MiMo-V2.5
Input1,048,576 tokens
Output131,072 tokens
Fri Jul 17 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Kimi K3 and MiMo-V2.5 support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Kimi K3

Text
Images
Audio
Video

MiMo-V2.5

Text
Images
Audio
Video

Release Timeline

When each model was launched

Kimi K3 was released on 2026-07-16, while MiMo-V2.5 was released on 2026-04-22.

Kimi K3 is 3 months newer than MiMo-V2.5.

Kimi K3

Jul 16, 2026

1 days ago

2mo newer
MiMo-V2.5

Apr 22, 2026

2 months ago

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

Kimi K3 is available from Moonshot AI. MiMo-V2.5 is available from Novita, DeepInfra.

Kimi K3

moonshot logo
Unknown Organization
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M

MiMo-V2.5

novita logo
Novita
Input Price:Input: $0.17/1MOutput Price:Output: $0.34/1M
deepinfra logo
Deepinfra
Input Price:Input: $0.40/1MOutput Price:Output: $2.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Key Takeaways

Higher CharXiv-R score (91.3% vs 81.0%)
Higher MMMU-Pro score (81.6% vs 77.9%)
Higher OmniDocBench score (91.1% vs 87.2%)
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Kimi K3 and MiMo-V2.5 side-by-side, then vote on the output you prefer.

Kimi K3
✓ Preferred
MiMo-V2.5
Open in Playground
AI Model Comparison Table
Feature
Moonshot AI
Kimi K3
Xiaomi
MiMo-V2.5

FAQ

Common questions about Kimi K3 vs MiMo-V2.5.

Which is better, Kimi K3 or MiMo-V2.5?

Kimi K3 significantly outperforms across most benchmarks. Kimi K3 is made by Moonshot AI and MiMo-V2.5 is made by Xiaomi. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Kimi K3 compare to MiMo-V2.5 in benchmarks?

Kimi K3 scores MathVision: 97.8%, DeepSearchQA: 95.0%, GPQA: 93.5%, CharXiv-R: 91.3%, BrowseComp: 91.2%. MiMo-V2.5 scores HR-Bench (4k): 88.5%, Video-MME: 87.7%, OmniDocBench: 87.2%, GraphWalks: 87.0%, DailyOmni: 83.5%.

Is Kimi K3 cheaper than MiMo-V2.5?

MiMo-V2.5 is 17.9x cheaper for input tokens. Kimi K3 costs $3.00/M input and $15.00/M output via moonshot. MiMo-V2.5 costs $0.17/M input and $0.34/M output via novita.

What are the context window sizes for Kimi K3 and MiMo-V2.5?

Kimi K3 supports 1.0M tokens and MiMo-V2.5 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 Kimi K3 and MiMo-V2.5?

Key differences include input pricing ($3.00 vs $0.17/M), licensing (Unknown vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Kimi K3 and MiMo-V2.5?

Kimi K3 is developed by Moonshot AI and MiMo-V2.5 is developed by Xiaomi.