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

    MoonshotAI: Kimi K2 0905

    Released Sep 4, 2025
    moonshotai/kimi-k2-0905
    text→text
    Set alert
    Ranked in:Text
    Try it on:
    OOpenRouter

    Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

    Best overall rank
    #90
    Across all subsets · overall
    Total arena votes
    64,074
    Across 27 (subset, category) entries
    Providers on OR
    3
    AtlasCloud + others
    First seen
    2026-05-08
    45 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.600
    Output (per 1M)
    $2.50

    Capabilities

    Modality
    text->text
    Context
    262K tokens
    Tokenizer
    Other
    Knowledge cutoff
    2024-12-31
    Max output
    262K tokens
    Moderation
    Unmoderated
    Hugging Face
    moonshotai/Kimi-K2-Instruct-0905
    Supported parameters
    frequency_penalty
    logit_bias
    max_tokens
    min_p
    presence_penalty
    repetition_penalty
    response_format
    seed
    stop
    structured_outputs
    temperature
    tool_choice
    tools
    top_k
    top_p

    Providers

    ProviderRegion / TagContextInput/MOutput/MUptime 1dLatencyQuantCache
    AtlasCloudatlas-cloud/fp8262K$0.600$2.5099.94%-
    fp8
    -
    Groqgroq262K$1.00$3.0099.94%--✓
    Novitanovita/fp8262K$0.600$2.5099.87%-
    fp8
    -

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #58Industry Legal And Government
    -
    1452780
    #72German
    -
    1421260
    #74Japanese
    -
    1375182
    #74Spanish
    -
    1419331
    #79Industry Medicine And Healthcare
    -
    1445719
    #83Coding
    -
    14682,241
    #86Industry Life And Physical And Social Science
    -
    14391,734
    #88Russian
    -
    1411699
    #90Exclude Ties
    -
    14068,573
    #90Overall
    -
    141811,780
    #91Chinese
    -
    1454735
    #91Industry Mathematical
    -
    1424641
    #91Math
    -
    1416759
    #93Korean
    -
    1354292
    #94Hard Prompts
    -
    14375,580
    #97Industry Software And It Services
    -
    14523,964
    #101Hard Prompts English
    -
    14392,840
    #102Creative Writing
    -
    13821,501
    #103English
    -
    14235,467
    #103Industry Entertainment And Sports And Media
    -
    13802,103
    #108Industry Business And Management And Financial Operations
    -
    14052,058
    #110French
    -
    1419183
    #115Industry Writing And Literature And Language
    -
    13812,593
    #115Multi Turn
    -
    14042,076
    #117Expert
    -
    1418555
    #117Instruction Following
    -
    13902,887
    #124Longer Query
    -
    14032,541