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

    Qwen: Qwen3 235B A22B Thinking 2507

    Released Jul 25, 2025
    qwen/qwen3-235b-a22b-thinking-2507
    text→text
    Set alert
    Ranked in:Text
    Try it on:
    OOpenRouter

    Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

    Best overall rank
    #112
    ▼ 1 vs 7d ago
    Total arena votes
    47,112
    Across 26 (subset, category) entries
    Providers on OR
    5
    WandB + others
    First seen
    2026-05-08
    26 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.100
    Output (per 1M)
    $0.100
    Cache Read (per 1M)
    $0.100

    Capabilities

    Modality
    text->text
    Context
    262K tokens
    Tokenizer
    Qwen3
    Knowledge cutoff
    2025-06-30
    Max output
    262K tokens
    Moderation
    Unmoderated
    Hugging Face
    Qwen/Qwen3-235B-A22B-Thinking-2507
    Supported parameters
    frequency_penalty
    include_reasoning
    logit_bias
    max_tokens
    min_p
    presence_penalty
    reasoning
    repetition_penalty
    response_format
    seed
    stop
    structured_outputs
    temperature
    tool_choice
    tools
    top_k
    top_p

    Providers

    ProviderRegion / TagContextInput/MOutput/MUptime 1dLatencyQuantCache
    WandBwandb/bf16262K$0.100$0.10099.98%-
    bf16
    -
    DeepInfradeepinfra/fp8262K$0.230$2.3099.84%-
    fp8
    -
    Novitanovita/fp8131K$0.300$3.0099.83%-
    fp8
    -
    AtlasCloudatlas-cloud/fp8128K$0.280$2.3099.44%-
    fp8
    -
    Alibabaalibaba131K$0.150$1.5099.27%---

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #55Expert
    -
    1464411
    #68Japanese
    -
    1374403
    #79Industry Mathematical
    -
    1426492
    #89Chinese
    -
    1450413
    #94German
    -
    1395203
    #95Russian
    -
    1403438
    #100Industry Medicine And Healthcare
    -
    1433522
    #100Korean
    -
    1348199
    #108Creative Writing
    -
    13741,077
    #108Industry Business And Management And Financial Operations
    -
    14021,546
    #110Hard Prompts English
    -
    14282,010
    #112Overall
    -
    14008,993
    #113Industry Software And It Services
    -
    14332,992
    #113Industry Writing And Literature And Language
    -
    13781,868
    #114Coding
    -
    14421,611
    #114Exclude Ties
    -
    13816,352
    #114Hard Prompts
    -
    14183,845
    #115Instruction Following
    -
    13862,100
    #116Math
    -
    1398490
    #116Spanish
    -
    1382154
    #120Industry Life And Physical And Social Science
    -
    14101,514
    #121Longer Query
    -
    14011,624
    #122Multi Turn
    -
    13941,401
    #123English
    -
    14054,374
    #125Industry Entertainment And Sports And Media
    -
    13521,541
    #137Industry Legal And Government
    -
    1390539