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

    Anthropic: Claude Sonnet 4.5

    Released Sep 29, 2025
    anthropic/claude-sonnet-4.5
    text+image+file→text
    Set alert
    Ranked in:TextWebDev
    Try it on:
    OOpenRouter

    Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

    Best overall rank
    #39
    ▼ 1 vs 7d ago
    Total arena votes
    1,064,999
    Across 62 (subset, category) entries
    Providers on OR
    7
    Amazon Bedrock + others
    First seen
    2026-05-08
    45 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $3.00
    Output (per 1M)
    $15.00
    Cache Read (per 1M)
    $0.300
    Cache Write (per 1M)
    $3.75

    Per unit

    Web search
    $0.010/call

    Capabilities

    Modality
    text+image+file->text
    Context
    1M tokens
    Tokenizer
    Claude
    Knowledge cutoff
    2025-01-31
    Max output
    64K tokens
    Moderation
    Moderated
    Supported parameters
    include_reasoning
    max_tokens
    reasoning
    response_format
    stop
    structured_outputs
    temperature
    tool_choice
    tools
    top_k
    top_p

    Providers

    ProviderRegion / TagContextInput/MOutput/MUptime 1dLatencyQuantCache
    Amazon Bedrockamazon-bedrock/eu-west-11M$3.00$15.00100.00%---
    Anthropicanthropic/21M$3.00$15.00100.00%---
    Googlegoogle-vertex/global1M$3.00$15.00100.00%---
    Googlegoogle-vertex/us-east51M$3.00$15.00100.00%---
    Amazon Bedrockamazon-bedrock1M$3.00$15.0099.81%---
    Anthropicanthropic1M$3.00$15.0099.39%---
    Amazon Bedrockanthropic/claude-on-aws1M$3.00$15.0081.45%---

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #18Coding
    thinking-32k
    152019,323
    #18Creative Writing
    -
    145412,059
    #18Longer Query
    thinking-32k
    148624,578
    #20Hard Prompts English
    thinking-32k
    149823,108
    #21Expert
    thinking-32k
    15015,464
    #21Longer Query
    -
    148424,992
    #22Instruction Following
    thinking-32k
    146523,658
    #23Creative Writing
    thinking-32k
    144712,330
    #23Industry Entertainment And Sports And Media
    thinking-32k
    144315,674
    #23Instruction Following
    -
    146423,319
    #24Coding
    -
    151419,175
    #24Hard Prompts English
    -
    149123,378
    #24Industry Writing And Literature And Language
    -
    145418,406
    #24Spanish
    -
    14642,169
    #26Multi Turn
    -
    147914,139
    #27Industry Business And Management And Financial Operations
    -
    146115,390
    #27Industry Entertainment And Sports And Media
    -
    144215,308
    #29Hard Prompts
    thinking-32k
    148746,941
    #29Industry Mathematical
    thinking-32k
    14723,911
    #29Industry Software And It Services
    thinking-32k
    150129,984
    #31English
    thinking-32k
    147238,959
    #32Expert
    -
    14865,571
    #32Industry Writing And Literature And Language
    thinking-32k
    145118,795
    #32Spanish
    thinking-32k
    14542,282
    #33French
    -
    14781,833
    #33German
    thinking-32k
    14551,300
    #33Hard Prompts
    -
    148446,593
    #34Industry Software And It Services
    -
    149829,730
    #35English
    -
    146838,641
    #35Korean
    -
    14151,256
    #35Math
    thinking-32k
    14554,913
    #37Industry Business And Management And Financial Operations
    thinking-32k
    145815,615
    #38Exclude Ties
    -
    145959,248
    #38Multi Turn
    thinking-32k
    147014,067
    #39Exclude Ties
    thinking-32k
    145960,671
    #39Overall
    thinking-32k
    145582,494
    #40French
    thinking-32k
    14761,872
    #40Overall
    -
    145580,950
    #41Industry Legal And Government
    -
    14645,775
    #41Industry Life And Physical And Social Science
    -
    147313,108
    #41Russian
    -
    14537,935
    #43Industry Legal And Government
    thinking-32k
    14625,704
    #44German
    -
    14441,297
    #45Russian
    thinking-32k
    14507,918
    #46Chinese
    thinking-32k
    14893,873
    #46Industry Medicine And Healthcare
    -
    14735,169
    #46Japanese
    -
    1409673
    #48Industry Life And Physical And Social Science
    thinking-32k
    147013,147
    #48Industry Mathematical
    -
    14533,988
    #50Industry Medicine And Healthcare
    thinking-32k
    14715,209
    #50Japanese
    thinking-32k
    1405693
    #56Korean
    thinking-32k
    13921,286
    #57Chinese
    -
    14823,867
    #73Math
    -
    14284,913

    WebDev

    RankCategoryVariantTrendEloVotes
    #42Webdev-react
    -
    13865,407
    #43Webdev-react
    thinking-32k
    13824,417
    #45Webdev
    thinking-32k
    138815,740
    #46Overall
    thinking-32k
    138815,741
    #48Webdev
    -
    138618,389
    #48Webdev-html
    thinking-32k
    139611,312
    #49Overall
    -
    138618,390
    #50Webdev-html
    -
    138612,952