Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
MiMo-V2.5-Pro
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and l
SharkScore
#75 in Models
Why it scores 45.6
MiMo-V2.5-Pro has a SharkScore of 45.6/100, ranked #75 of 608 in Models (updated 2026-11-19).
Each part compares MiMo-V2.5-Pro with other listings in Models. Evidence covers 87% of the score's weight.
- Adoption
- 0 · 30%
- User reviews
- no data · 25%
- Maintenance
- 86 · 20%
- Trust & transparency
- 80 · 15%
- Momentum
- no data · 10%
Paying never changes this score. How ranking works · method v2026-11-18.2
RankShark review of MiMo-V2.5-Pro
Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review
We were not paid for this review.
As of 2026-11-18, MiMo-V2.5-Pro is an open-weight text model with a 1,024,000-token context window and OpenRouter-listed usage pricing of $0.435 per million input tokens and $0.87 per million output tokens. [E1][E2]
Xiaomi’s Mixture-of-Experts language model has 1.02T total parameters, 42B active parameters, and a 1M-token context length. The model card lists an MIT license; OpenRouter lists text input and text output. [E1][E2]
Best for
- Developers working on long-context tasks. · model card
- Teams building agentic or complex software-engineering workflows. · model card
- Teams that want a model they can deploy with SGLang or vLLM. · model card
Not for
- Teams that need image, audio, or other non-text input or output. · OpenRouter
Key features
- Long context. The vendor says the model supports up to 1M tokens of context. · model card
- Mixture-of-Experts architecture. The vendor says the model has 1.02T total parameters and 42B active parameters. · model card
- Hybrid attention. The vendor says the model interleaves Sliding Window Attention and Global Attention at a 6:1 ratio. · model card
- Multi-Token Prediction. The vendor says the model uses three MTP modules. · model card
- Deployment options. The vendor provides deployment examples for SGLang and vLLM. · model card
- OpenRouter API options. OpenRouter lists chat completions, completions, messages, and responses endpoints for the model. · OpenRouter
Pros
- The model card lists an MIT license. · model card
- The model card describes a context length of up to 1M tokens. · model card
- The model card includes deployment examples for SGLang and vLLM. · model card
Cons
- OpenRouter lists text-only input and output, so the listing does not offer image or audio modalities. · OpenRouter
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.
Pricing
| Plan | Price | Limits |
|---|---|---|
| OpenRouter token usage | $0.435 per 1M input tokens; $0.87 per 1M output tokens | OpenRouter lists a 1,024,000-token context length. |
Checked 18 Nov 2026
- Free plan
- Not stated (checked 18 Nov 2026)
- Free trial
- Not stated (checked 18 Nov 2026)
- Trains on customer data
- Not stated (checked 18 Nov 2026)
- Data retention
- Not stated (checked 18 Nov 2026)
- Data regions
- Not stated (checked 18 Nov 2026)
- Data processing agreement
- Not stated (checked 18 Nov 2026)
- AI models used
- MiMo-V2.5-Pro; 1.02T total parameters, 42B active parameters. · model card
- API
- OpenRouter lists /api/v1/chat/completions, /api/v1/completions, /api/v1/messages, and /api/v1/responses. · OpenRouter
- SDKs
- Not stated (checked 18 Nov 2026)
- Webhooks
- Not stated (checked 18 Nov 2026)
- Platforms
- The model card links Hugging Face and ModelScope downloads and provides SGLang and vLLM deployment examples. · model card
- Security claims
- No security certification stated (checked 18 Nov 2026)
What we measured
- Context window (OpenRouter listing) · now
- 1,024,000 tokens
- Price per million tokens (OpenRouter listing) · now
- $0.435 in, $0.87 out
- Package downloads · 30 days
- 9,069
How we tested · sources
- Hourly uptime and response-time checks of the product's URL.
- Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
- We did not sign up, pay, or use the product as a customer.
- model card: https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro · fetched 18 Nov 2026
- OpenRouter: https://openrouter.ai/xiaomi/mimo-v2.5-pro · fetched 18 Nov 2026
- 18 Nov 2026: Plans or prices changed on the pricing page.
- 18 Nov 2026: Plans or prices changed on the pricing page.
Something wrong? Report an error with a public link that shows it; corrections re-run the review.
Top alternatives to MiMo-V2.5-Pro
See all- 67.1ModelOpen source
- 65.5
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t
ModelOpen source - 64.7
Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
ModelOpen source - 64.3
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
ModelOpen source