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 30B A3B

    Released Apr 28, 2025
    qwen/qwen3-30b-a3b
    text→text
    Set alert
    Ranked in:Text
    Try it on:
    OOpenRouter

    Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

    Best overall rank
    #196
    Across all subsets · overall
    Total arena votes
    138,964
    Across 27 (subset, category) entries
    Providers on OR
    4
    Alibaba + others
    First seen
    2026-05-08
    26 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.090
    Output (per 1M)
    $0.450

    Capabilities

    Modality
    text->text
    Context
    131K tokens
    Tokenizer
    Qwen3
    Knowledge cutoff
    2025-03-31
    Max output
    20K tokens
    Moderation
    Unmoderated
    Deprecates
    2026-06-05
    Hugging Face
    Qwen/Qwen3-30B-A3B
    Supported parameters
    frequency_penalty
    include_reasoning
    logit_bias
    logprobs
    max_tokens
    min_p
    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
    Alibabaalibaba131K$0.130$0.52099.99%---
    DeepInfradeepinfra/fp841K$0.090$0.45099.84%-
    fp8
    -
    NextBitnextbit/fp833K$0.140$0.55084.96%-
    fp8
    -
    Novitanovita/fp841K$0.090$0.45079.78%-
    fp8
    -

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #146French
    -
    1367322
    #147Japanese
    -
    1251665
    #150Industry Mathematical
    -
    13681,579
    #163Chinese
    -
    13711,253
    #163Korean
    -
    1267440
    #164Math
    -
    13531,708
    #165Spanish
    -
    1324410
    #170Expert
    -
    13441,315
    #171German
    -
    1303727
    #173Coding
    -
    13874,531
    #182Industry Business And Management And Financial Operations
    -
    13304,014
    #182Industry Software And It Services
    -
    13718,314
    #182Longer Query
    -
    13404,460
    #183Hard Prompts English
    -
    13625,814
    #186Hard Prompts
    -
    134510,694
    #194English
    -
    134613,396
    #196Overall
    -
    132726,495
    #197Exclude Ties
    -
    127618,355
    #197Industry Medicine And Healthcare
    -
    13361,622
    #197Multi Turn
    -
    13214,523
    #198Russian
    -
    13061,908
    #200Instruction Following
    -
    13116,129
    #201Industry Writing And Literature And Language
    -
    13055,970
    #207Creative Writing
    -
    12853,366
    #208Industry Life And Physical And Social Science
    -
    13334,612
    #219Industry Entertainment And Sports And Media
    -
    12714,573
    #225Industry Legal And Government
    -
    13231,769