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 Next 80B A3B Instruct

    Released Sep 11, 2025
    qwen/qwen3-next-80b-a3b-instruct
    text→text
    Set alert
    Ranked in:Text
    Try it on:
    OOpenRouter

    Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...

    Best overall rank
    #109
    ▼ 1 vs 7d ago
    Total arena votes
    126,942
    Across 27 (subset, category) entries
    Providers on OR
    6
    Alibaba + others
    First seen
    2026-05-08
    26 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.090
    Output (per 1M)
    $1.10

    Capabilities

    Modality
    text->text
    Context
    262K tokens
    Tokenizer
    Qwen3
    Knowledge cutoff
    2025-09-30
    Max output
    16K tokens
    Moderation
    Unmoderated
    Hugging Face
    Qwen/Qwen3-Next-80B-A3B-Instruct
    Supported parameters
    frequency_penalty
    logit_bias
    max_tokens
    min_p
    presence_penalty
    repetition_penalty
    response_format
    seed
    stop
    structured_outputs
    temperature
    tool_choice
    tools
    top_k
    top_p

    Providers

    ProviderRegion / TagContextInput/MOutput/MUptime 1dLatencyQuantCache
    Alibabaalibaba131K$0.098$0.78099.97%---
    Novitanovita/bf16131K$0.150$1.5099.92%-
    bf16
    -
    Parasailparasail/fp8262K$0.100$1.1099.92%-
    fp8
    -
    Googlegoogle-vertex/global262K$0.150$1.2099.81%---
    AtlasCloudatlas-cloud/fp8262K$0.150$1.5099.41%-
    fp8
    -
    DeepInfradeepinfra/fp8262K$0.090$1.1098.94%-
    fp8
    -

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #63Japanese
    -
    1378268
    #67Spanish
    -
    1422615
    #81Math
    -
    14191,212
    #85Chinese
    -
    14551,183
    #86Industry Medicine And Healthcare
    -
    14391,177
    #92Industry Business And Management And Financial Operations
    -
    14124,281
    #93Industry Mathematical
    -
    14171,050
    #97Industry Software And It Services
    -
    14448,121
    #100German
    -
    1388459
    #103Industry Legal And Government
    -
    14131,426
    #107Hard Prompts
    -
    142111,901
    #108Coding
    -
    14464,794
    #108Hard Prompts English
    -
    14296,060
    #109Industry Life And Physical And Social Science
    -
    14173,508
    #109Multi Turn
    -
    14044,084
    #109Overall
    -
    140222,881
    #110Exclude Ties
    -
    138416,190
    #115English
    -
    141210,892
    #116French
    -
    1406347
    #116Russian
    -
    13871,188
    #123Korean
    -
    1324484
    #127Instruction Following
    -
    13796,314
    #128Longer Query
    -
    13915,217
    #134Expert
    -
    13961,004
    #149Industry Entertainment And Sports And Media
    -
    13294,204
    #151Industry Writing And Literature And Language
    -
    13455,050
    #165Creative Writing
    -
    13173,032

    Related models

    Qwen: Qwen3 Next 80B A3B Instruct (free)qwen/qwen3-next-80b-a3b-instruct:free