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

    Z.ai: GLM 5.2

    Released Jun 16, 2026
    z-ai/glm-5.2
    text→text
    Set alert
    Ranked in:TextWebDev
    Try it on:
    OOpenRouter

    GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

    Best overall rank
    #2
    Across all subsets · overall
    Total arena votes
    73,752
    Across 29 (subset, category) entries
    Providers on OR
    27
    WandB + others
    First seen
    2026-06-17
    21 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.930
    Output (per 1M)
    $3.00
    Cache Read (per 1M)
    $0.180

    Capabilities

    Modality
    text->text
    Context
    1M tokens
    Tokenizer
    Other
    Max output
    33K tokens
    Moderation
    Unmoderated
    Hugging Face
    zai-org/GLM-5.2
    Supported parameters
    frequency_penalty
    include_reasoning
    logit_bias
    logprobs
    max_tokens
    min_p
    parallel_tool_calls
    presence_penalty
    reasoning
    reasoning_effort
    repetition_penalty
    response_format
    seed
    stop
    structured_outputs
    temperature
    tool_choice
    tools
    top_k
    top_logprobs
    top_p

    Providers

    ProviderRegion / TagContextInput/MOutput/MUptime 1dLatencyQuantCache
    WandBwandb/fp4262K$1.39$4.4099.98%-
    fp4
    -
    Waferwafer/fast1M$3.00$10.2599.94%-
    fp4
    -
    Alibabaalibaba1M$1.32$4.1499.90%---
    StreamLakestreamlake/fp81M$1.26$3.9699.83%-
    fp8
    -
    AtlasCloudatlas-cloud/fp81M$1.26$3.9699.79%-
    fp8
    -
    Z.AIz-ai/fp81M$1.40$4.4099.78%-
    fp8
    -
    Fireworksfireworks/fast1M$2.10$6.6099.77%---
    SiliconFlowsiliconflow/fp81M$1.30$4.0999.75%-
    fp8
    -
    Baidubaidu/fp81M$1.12$3.9699.69%-
    fp8
    -
    Novitanovita/fp81M$0.980$3.0899.47%-
    fp8
    -
    Parasailparasail/fp4262K$1.40$4.4099.42%-
    fp4
    -
    Waferwafer/fp41M$1.20$4.1099.39%-
    fp4
    -
    Togethertogether262K$1.40$4.4099.36%---
    Fireworksfireworks1M$1.40$4.4099.28%---
    AkashMLakashml/fp8224K$1.30$4.4098.86%-
    fp8
    -
    DeepInfradeepinfra/fp41M$0.930$3.0098.26%-
    fp4
    -
    Ambientambient/fp8101K$1.40$4.4097.75%-
    fp8
    -
    Venicevenice/fp81M$1.40$4.4097.44%-
    fp8
    -
    Io Netio-net/fp8262K$1.45$4.5497.44%-
    fp8
    -
    GMICloudgmicloud/fp81M$0.980$3.0896.89%-
    fp8
    -
    Phalaphala1M$1.40$4.4096.72%---
    Morphmorph1M$1.10$4.1096.36%---
    Inceptroninceptron/fp41M$0.970$3.0896.21%-
    fp4
    -
    Cloudflarecloudflare262K$1.40$4.4095.10%---
    DigitalOceandigitalocean262K$1.05$4.4093.51%---
    Decartdecart/fp41M$1.20$4.2081.49%-
    fp4
    -
    Friendlifriendli1M$1.40$4.4079.19%---

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    ★ #4Spanish
    harness: max
    1490306
    #8Industry Life And Physical And Social Science
    harness: max
    15031,566
    #17Industry Medicine And Healthcare
    harness: max
    1491717
    #18French
    harness: max
    1494347
    #19Instruction Following
    harness: max
    14663,116
    #20Hard Prompts English
    harness: max
    14963,078
    #20Industry Mathematical
    harness: max
    1486507
    #21Coding
    harness: max
    15152,520
    #21English
    harness: max
    14794,545
    #21Expert
    harness: max
    1500892
    #22Chinese
    harness: max
    1509477
    #23Longer Query
    harness: max
    14814,136
    #24Industry Writing And Literature And Language
    harness: max
    14552,425
    #24Math
    harness: max
    1472474
    #25Russian
    harness: max
    1470914
    #26Exclude Ties
    harness: max
    14756,912
    #26Hard Prompts
    harness: max
    14906,018
    #26Industry Legal And Government
    harness: max
    1476744
    #26Overall
    harness: max
    14699,338
    #31Creative Writing
    harness: max
    14451,732
    #31Industry Entertainment And Sports And Media
    harness: max
    14382,230
    #31Non English
    harness: max
    14524,788
    #32Industry Software And It Services
    harness: max
    15003,580
    #38Industry Business And Management And Financial Operations
    harness: max
    14581,862
    #46Multi Turn
    harness: max
    14641,484

    WebDev

    RankCategoryVariantTrendEloVotes
    ★ #2Overall
    harness: max
    15843,015
    ★ #2Webdev
    harness: max
    15843,015
    ★ #2Webdev-react
    harness: max
    15882,606
    #7Webdev-html
    harness: max
    1534408