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 · Non English

    Microsoft: Phi 4

    Released Jan 10, 2025
    microsoft/phi-4
    text→text
    Set alert
    Ranked in:Text
    Try it on:
    OOpenRouter

    [Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

    Best overall rank
    #273
    ▼ 1 vs 7d ago
    Total arena votes
    134,122
    Across 28 (subset, category) entries
    Providers on OR
    1
    DeepInfra
    First seen
    2026-05-08
    61 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.070
    Output (per 1M)
    $0.140

    Capabilities

    Modality
    text->text
    Context
    16K tokens
    Tokenizer
    Other
    Knowledge cutoff
    2024-06-30
    Max output
    16K tokens
    Moderation
    Unmoderated
    Hugging Face
    microsoft/phi-4
    Supported parameters
    frequency_penalty
    logit_bias
    max_tokens
    min_p
    presence_penalty
    repetition_penalty
    response_format
    seed
    stop
    structured_outputs
    temperature
    top_k
    top_p

    Providers

    ProviderRegion / TagContextInput/MOutput/MUptime 1dLatencyQuantCache
    DeepInfradeepinfra/bf1616K$0.070$0.140100.00%-
    bf16
    -

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #193Japanese
    -
    1195500
    #206Korean
    -
    1196319
    #212French
    -
    1266205
    #212German
    -
    1256523
    #212Spanish
    -
    1265127
    #234Industry Mathematical
    -
    12792,350
    #241Expert
    -
    12661,124
    #244Math
    -
    12652,764
    #251Industry Legal And Government
    -
    12981,341
    #257Chinese
    -
    12671,503
    #257Hard Prompts English
    -
    12903,804
    #257Industry Medicine And Healthcare
    -
    12721,037
    #259Coding
    -
    13063,305
    #261Hard Prompts
    -
    12785,747
    #263Industry Software And It Services
    -
    12905,580
    #263Russian
    -
    12452,576
    #264Industry Business And Management And Financial Operations
    -
    12562,438
    #265Longer Query
    -
    12662,896
    #267Instruction Following
    -
    12459,162
    #267Multi Turn
    -
    12423,517
    #271English
    -
    127214,101
    #272Non English
    -
    123310,025
    #273Exclude Ties
    -
    115715,789
    #273Industry Writing And Literature And Language
    -
    12296,470
    #273Overall
    -
    125624,126
    #274Creative Writing
    -
    12104,062
    #274Industry Life And Physical And Social Science
    -
    12654,245
    #275Industry Entertainment And Sports And Media
    -
    12024,486