ZMIME
Comparison · 3 models · Updated Nov 18, 2026

MiMo-V2.5-Pro vs MiMo-V2.5-Pro-UltraSpeed vs Seed Evolving

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. Xiaomi

    MiMo-V2.5-Pro

    Released Apr 22, 2026Deprecated

    47/100
    • ECI—
    • Price$0.435 / $0.87
    • Context1.05M
  2. Xiaomi

    MiMo-V2.5-Pro-UltraSpeed

    Released Jun 8, 2026Deprecated

    47/100
    • ECI—
    • Price$1.30 / $2.61
    • Context1.05M
  3. ByteDance Seed

    Seed Evolving

    Released Jun 23, 2026

    74/100
    • ECI—
    • Price$0.891 / $4.45
    • Context1.02M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Seed Evolving 74/100, MiMo-V2.5-Pro 47/100, MiMo-V2.5-Pro-UltraSpeed 47/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceMiMo-V2.5-ProMiMo-V2.5-Pro $0.544 · MiMo-V2.5-Pro-UltraSpeed $1.63 · Seed Evolving $1.78 per 1M tokens (3:1 blend)
  • Longest contextMiMo-V2.5-Pro and MiMo-V2.5-Pro-UltraSpeedMiMo-V2.5-Pro 1,048,576 · MiMo-V2.5-Pro-UltraSpeed 1,048,576 · Seed Evolving 1,024,000 tokens
  • Widest inputsSeed EvolvingMiMo-V2.5-Pro: Text · MiMo-V2.5-Pro-UltraSpeed: Text · Seed Evolving: Text, Images, Video
  • Self-hostingMiMo-V2.5-Pro and MiMo-V2.5-Pro-UltraSpeedPublishes downloadable weights
How the score is built
MeasureWeightMiMo-V2.5-ProMiMo-V2.5-Pro-UltraSpeedSeed Evolving
Inputs & features60%353580
Context window40%656565
Specs only100%47/10047/10074/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

MiMo-V2.5-Pro vs MiMo-V2.5-Pro-UltraSpeed vs Seed Evolving specifications side by side
SpecificationMiMo-V2.5-ProXiaomiMiMo-V2.5-Pro-UltraSpeedXiaomiSeed EvolvingByteDance Seed
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.435 (best)$1.30$0.891
Output$0.87 (best)$2.61$4.45
Cached input$0.0036 (best)$0.011$0.178
Blended (3:1)$0.544 (best)$1.63$1.78
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Xiaomi APIOfficial Xiaomi APIOfficial Volcengine Ark API
Limits
Context window1,048,576 tokens (best)1,048,576 tokens (best)1,024,000 tokens
Max output131,072 tokens131,072 tokens256,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesYesminimal · low · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenOpenProprietary
API model IDmimo-v2.5-promimo-v2.5-pro-ultraspeeddoubao-seed-evolving
API providers15 (best)12
ReleasedApr 22, 2026Jun 8, 2026Jun 23, 2026
Knowledge cutoffDec 2024Dec 2024—
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • MiMo-V2.5-Pro$6.09
  • MiMo-V2.5-Pro-UltraSpeed$18.27
  • Seed Evolving$17.81
04 — Questions

Which should you choose?

Which is better: MiMo-V2.5-Pro, MiMo-V2.5-Pro-UltraSpeed or Seed Evolving?

There is not enough shared capability evidence to name an overall winner. The scores (Seed Evolving 74/100, MiMo-V2.5-Pro 47/100, MiMo-V2.5-Pro-UltraSpeed 47/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, MiMo-V2.5-Pro, MiMo-V2.5-Pro-UltraSpeed or Seed Evolving?

MiMo-V2.5-Pro is cheaper at $0.435 input / $0.87 output per million tokens (official Xiaomi API price). MiMo-V2.5-Pro-UltraSpeed costs $1.30 input / $2.61 output per million tokens (official Xiaomi API price); Seed Evolving costs $0.891 input / $4.45 output per million tokens (official Volcengine Ark API price). At a typical mix of three input tokens to one output token, that is $0.544 per million tokens for MiMo-V2.5-Pro versus $1.63 for MiMo-V2.5-Pro-UltraSpeed (3× as much) and $1.78 for Seed Evolving (3.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. MiMo-V2.5-Pro has not been scored yet, MiMo-V2.5-Pro-UltraSpeed has not been scored yet and Seed Evolving has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for MiMo-V2.5-Pro, MiMo-V2.5-Pro-UltraSpeed and Seed Evolving yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

MiMo-V2.5-Pro and MiMo-V2.5-Pro-UltraSpeed have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,024,000 for Seed Evolving. Maximum output per response: MiMo-V2.5-Pro up to 131,072, MiMo-V2.5-Pro-UltraSpeed up to 131,072, Seed Evolving up to 256,000 tokens.

Which can read images, PDFs, audio or video?

MiMo-V2.5-Pro accepts text; MiMo-V2.5-Pro-UltraSpeed accepts text; Seed Evolving accepts text, images and video. Seed Evolving handles the widest range of inputs.

Are any of these open source?

MiMo-V2.5-Pro and MiMo-V2.5-Pro-UltraSpeed publishes its weights and can be self-hosted; Seed Evolving is proprietary.

Which is newer?

Seed Evolving is the newest, released Jun 23, 2026. MiMo-V2.5-Pro-UltraSpeed came out Jun 8, 2026; MiMo-V2.5-Pro came out Apr 22, 2026. Knowledge cutoff: MiMo-V2.5-Pro Dec 2024, MiMo-V2.5-Pro-UltraSpeed Dec 2024.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.