ZMIME
Comparison · 3 models · Updated Nov 18, 2026

MiMo-V2.5 vs Gemini 3.1 Flash Lite vs Gemma 4 E4B IT

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

Price in rating: Included · Exclude price

  1. Xiaomi

    MiMo-V2.5

    Released Apr 22, 2026Deprecated

    78/100
    • ECI—
    • Price$0.14 / $0.28
    • Context1.05M
  2. Google

    Gemini 3.1 Flash Lite

    Released May 7, 2026

    72/100
    • ECI—
    • Price$0.25 / $1.50
    • Context1.05M
  3. Google

    Gemma 4 E4B IT

    Released Apr 2, 2026

    70/100
    • ECI—
    • Price$0.085 / $0.35
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (MiMo-V2.5 78/100, Gemini 3.1 Flash Lite 72/100, Gemma 4 E4B IT 70/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceGemma 4 E4B ITGemma 4 E4B IT $0.151 · MiMo-V2.5 $0.175 · Gemini 3.1 Flash Lite $0.563 per 1M tokens (3:1 blend)
  • Longest contextMiMo-V2.5 and Gemini 3.1 Flash LiteMiMo-V2.5 1,048,576 · Gemini 3.1 Flash Lite 1,048,576 · Gemma 4 E4B IT 131,072 tokens
  • Widest inputsGemini 3.1 Flash LiteMiMo-V2.5: Text, Images, Audio, Video · Gemini 3.1 Flash Lite: Text, Images, PDFs, Audio, Video · Gemma 4 E4B IT: Text, Images, Audio
  • Self-hostingMiMo-V2.5 and Gemma 4 E4B ITPublishes downloadable weights
How the score is built
MeasureWeightMiMo-V2.5Gemini 3.1 Flash LiteGemma 4 E4B IT
Price50%825985
Inputs & features30%8010070
Context window20%656532
Specs & price only100%78/10072/10070/100

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 vs Gemini 3.1 Flash Lite vs Gemma 4 E4B IT specifications side by side
SpecificationMiMo-V2.5XiaomiGemini 3.1 Flash LiteGoogleGemma 4 E4B ITGoogle
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.14$0.25$0.085 (best)
Output$0.28 (best)$1.50$0.35
Cached input$0.0028 (best)$0.025—
Blended (3:1)$0.175$0.563$0.151 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Xiaomi APIOfficial Google APIMedian of 2 providers
Limits
Context window1,048,576 tokens (best)1,048,576 tokens (best)131,072 tokens
Max output131,072 tokens (best)65,536 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesNo
AudioYesYesYes
VideoYesYesNo
ReasoningYesYesminimal · low · medium · highYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenProprietaryOpen
API model IDmimo-v2.5gemini-3.1-flash-lite—
API providers1826 (best)3
ReleasedApr 22, 2026May 7, 2026Apr 2, 2026
Knowledge cutoffDec 2024Jan 2025—
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$1.96
  • Gemini 3.1 Flash Lite$5.50
  • Gemma 4 E4B IT$1.55
04 — Questions

Which should you choose?

Which is better: MiMo-V2.5, Gemini 3.1 Flash Lite or Gemma 4 E4B IT?

There is not enough shared capability evidence to name an overall winner. The scores (MiMo-V2.5 78/100, Gemini 3.1 Flash Lite 72/100, Gemma 4 E4B IT 70/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, MiMo-V2.5, Gemini 3.1 Flash Lite or Gemma 4 E4B IT?

Gemma 4 E4B IT is cheaper at $0.085 input / $0.35 output per million tokens (median across 2 API providers). MiMo-V2.5 costs $0.14 input / $0.28 output per million tokens (official Xiaomi API price); Gemini 3.1 Flash Lite costs $0.25 input / $1.50 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $0.151 per million tokens for Gemma 4 E4B IT versus $0.175 for MiMo-V2.5 (1.2× as much) and $0.563 for Gemini 3.1 Flash Lite (3.7× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. MiMo-V2.5 has not been scored yet, Gemini 3.1 Flash Lite has not been scored yet and Gemma 4 E4B IT has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for MiMo-V2.5, Gemini 3.1 Flash Lite and Gemma 4 E4B IT 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 and Gemini 3.1 Flash Lite have the largest context windows (1,048,576 and 1,048,576 tokens), against 131,072 for Gemma 4 E4B IT. Maximum output per response: MiMo-V2.5 up to 131,072, Gemini 3.1 Flash Lite up to 65,536, Gemma 4 E4B IT up to 8,192 tokens.

Which can read images, PDFs, audio or video?

MiMo-V2.5 accepts text, images, audio and video; Gemini 3.1 Flash Lite accepts text, images, PDFs, audio and video; Gemma 4 E4B IT accepts text, images and audio. Gemini 3.1 Flash Lite handles the widest range of inputs.

Are any of these open source?

MiMo-V2.5 and Gemma 4 E4B IT publishes its weights and can be self-hosted; Gemini 3.1 Flash Lite is proprietary.

Which is newer?

Gemini 3.1 Flash Lite is the newest, released May 7, 2026. MiMo-V2.5 came out Apr 22, 2026; Gemma 4 E4B IT came out Apr 2, 2026. Knowledge cutoff: MiMo-V2.5 Dec 2024, Gemini 3.1 Flash Lite Jan 2025.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.