gpt·basedElo-ranked, value-sorted
Sign in

Stay updated

Get an email when a cheaper, stronger model than yours appears on the leaderboard. No spam.

gpt·based

The LLM leaderboard that tells you when to switch. Arena rankings joined with OpenRouter pricing, refreshed daily.

Use cases

  • Best for coding
  • Best for multilingual
  • Cheapest worth using
  • Compare two models

Browse

  • Text models
  • WebDev models
  • Vision models
  • Image generation
  • Image edit

Data sources

  • LMArena
  • Providers

Developers

  • API on RapidAPI
  • OpenAPI spec

Contact

  • Contact page
  • [email protected]
© 2026 gptbasedDaily refresh, never paid placement.
    gpt·basedElo-ranked, value-sorted
    Sign in
    Back to Text · Overall

    Xiaomi: MiMo-V2.5-Pro

    Released Apr 22, 2026
    xiaomi/mimo-v2.5-pro
    text→text
    Set alert
    Ranked in:TextWebDev
    Try it on:
    OOpenRouter

    MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....

    Best overall rank
    #21
    ▼ 2 vs 7d ago
    Total arena votes
    189,189
    Across 31 (subset, category) entries
    Providers on OR
    4
    DeepInfra + others
    First seen
    2026-05-08
    45 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.435
    Output (per 1M)
    $0.870
    Cache Read (per 1M)
    $0.0036

    Capabilities

    Modality
    text->text
    Context
    1M tokens
    Tokenizer
    Other
    Max output
    131K tokens
    Moderation
    Unmoderated
    Hugging Face
    XiaomiMiMo/MiMo-V2.5-Pro
    Supported parameters
    frequency_penalty
    include_reasoning
    logit_bias
    logprobs
    max_tokens
    min_p
    presence_penalty
    reasoning
    repetition_penalty
    response_format
    seed
    stop
    structured_outputs
    temperature
    tool_choice
    tools
    top_k
    top_logprobs
    top_p

    Providers

    ProviderRegion / TagContextInput/MOutput/MUptime 1dLatencyQuantCache
    DeepInfradeepinfra/fp81M$1.00$3.0099.75%-
    fp8
    -
    Xiaomixiaomi/fp81M$0.435$0.87099.73%-
    fp8
    -
    Novitanovita1M$0.522$1.0499.73%---
    DigitalOceandigitalocean262K$0.800$3.0099.06%---

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #7Industry Mathematical
    -
    15051,428
    #8Korean
    -
    1458427
    #9Hard Prompts English
    -
    15088,391
    #11Expert
    -
    15132,300
    #12French
    -
    1501970
    #14Math
    -
    14851,384
    #15English
    -
    148312,148
    #15Instruction Following
    -
    14738,711
    #15Longer Query
    -
    148811,280
    #17Coding
    -
    15207,282
    #17Industry Life And Physical And Social Science
    -
    14924,343
    #18Chinese
    -
    15131,367
    #19Hard Prompts
    -
    149617,321
    #19Spanish
    -
    1466769
    #20Industry Software And It Services
    -
    150710,540
    #22Industry Business And Management And Financial Operations
    -
    14685,193
    #25Japanese
    -
    1438261
    #26Industry Entertainment And Sports And Media
    -
    14435,585
    #27Industry Legal And Government
    -
    14742,082
    #28Industry Writing And Literature And Language
    -
    14516,435
    #29Overall
    -
    146626,563
    #30Multi Turn
    -
    14764,662
    #31Exclude Ties
    -
    147120,438
    #33Russian
    -
    14612,980
    #35Industry Medicine And Healthcare
    -
    14781,889
    #39Creative Writing
    -
    14354,303
    #56German
    -
    1437418

    WebDev

    RankCategoryVariantTrendEloVotes
    #19Webdev
    -
    14685,966
    #21Overall
    -
    14716,887
    #21Webdev-react
    -
    14656,064
    #22Webdev-html
    -
    1473802