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 · Polish

    Qwen: Qwen3 VL 235B A22B Thinking

    Released Sep 23, 2025
    qwen/qwen3-vl-235b-a22b-thinking
    text+image→text
    Set alert
    Ranked in:TextVision
    Try it on:
    OOpenRouter

    Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....

    Best overall rank
    #65
    ▼ 2 vs 7d ago
    Total arena votes
    53,895
    Across 32 (subset, category) entries
    Providers on OR
    2
    Novita + others
    First seen
    2026-05-08
    61 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.260
    Output (per 1M)
    $2.60

    Capabilities

    Modality
    text+image->text
    Context
    131K tokens
    Tokenizer
    Qwen3
    Knowledge cutoff
    2025-03-31
    Max output
    33K tokens
    Moderation
    Unmoderated
    Hugging Face
    Qwen/Qwen3-VL-235B-A22B-Thinking
    Supported parameters
    frequency_penalty
    include_reasoning
    logprobs
    max_tokens
    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
    Novitanovita/bf16131K$0.980$3.9599.95%-
    bf16
    -
    Alibabaalibaba131K$0.260$2.6095.04%---

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #76German
    thinking
    1420170
    #84Korean
    thinking
    1363211
    #85Industry Mathematical
    thinking
    1432378
    #101Expert
    thinking
    1433381
    #109Chinese
    thinking
    1440296
    #109Coding
    thinking
    14561,626
    #114Math
    thinking
    1405428
    #116Industry Software And It Services
    thinking
    14372,837
    #119Polish
    thinking
    1377390
    #121Hard Prompts
    thinking
    14194,040
    #121Spanish
    thinking
    1385331
    #122Non English
    thinking
    13824,052
    #123Longer Query
    thinking
    14071,727
    #124Industry Entertainment And Sports And Media
    thinking
    13611,447
    #125Industry Legal And Government
    thinking
    1405512
    #125Overall
    thinking
    13967,939
    #128Industry Business And Management And Financial Operations
    thinking
    13921,583
    #129Industry Medicine And Healthcare
    thinking
    1415432
    #130Exclude Ties
    thinking
    13735,581
    #130Instruction Following
    thinking
    13842,132
    #132Industry Life And Physical And Social Science
    thinking
    14061,249
    #133Russian
    thinking
    1378482
    #134English
    thinking
    14043,887
    #135Hard Prompts English
    thinking
    14202,098
    #139Industry Writing And Literature And Language
    thinking
    13661,754
    #142Multi Turn
    thinking
    13881,287
    #150Creative Writing
    thinking
    13391,032

    Vision

    RankCategoryVariantTrendEloVotes
    #60Homework
    thinking
    1229311
    #62Diagram
    thinking
    1211480
    #62English
    thinking
    11981,103
    #63Ocr
    thinking
    12011,357
    #65Overall
    thinking
    11902,362