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 · Japanese

    Qwen: Qwen3 Next 80B A3B Instruct

    Released Sep 11, 2025
    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
    #126
    ▼ 2 vs 7d ago
    Total arena votes
    139,738
    Across 29 (subset, category) entries
    Providers on OR
    5
    Novita + others
    First seen
    2026-05-08
    72 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.100
    Output (per 1M)
    $1.10
    Cache Read (per 1M)
    $0.070

    Capabilities

    Modality
    text->text
    Context
    262K tokens
    Tokenizer
    Qwen3
    Knowledge cutoff
    2025-09-30
    Max output
    262K tokens
    Moderation
    Unmoderated
    Hugging Face
    Qwen/Qwen3-Next-80B-A3B-Instruct
    Supported parameters
    frequency_penalty
    logit_bias
    logprobs
    max_tokens
    min_p
    presence_penalty
    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$0.150$1.5099.99%-
    bf16
    -
    Alibabaalibaba131K$0.098$0.78099.99%---
    Parasailparasail/fp8262K$0.100$1.1099.97%-
    fp8
    -
    Googlegoogle-vertex/global262K$0.150$1.2099.64%---
    DeepInfradeepinfra/fp8262K$0.090$1.1099.33%-
    fp8
    -

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #74Japanese
    -
    1379268
    #76Spanish
    -
    1423613
    #82Non English
    -
    140811,936
    #95Math
    -
    14191,212
    #99Industry Medicine And Healthcare
    -
    14401,169
    #101Chinese
    -
    14531,183
    #108German
    -
    1389459
    #109Industry Business And Management And Financial Operations
    -
    14124,276
    #110Industry Mathematical
    -
    14161,044
    #115Industry Software And It Services
    -
    14438,111
    #120Industry Legal And Government
    -
    14141,424
    #122Hard Prompts
    -
    142111,896
    #124Hard Prompts English
    -
    14296,057
    #124Multi Turn
    -
    14044,082
    #125Coding
    -
    14464,790
    #125Polish
    -
    1374990
    #126Exclude Ties
    -
    138416,153
    #126Overall
    -
    140122,855
    #128Industry Life And Physical And Social Science
    -
    14173,506
    #129French
    -
    1404347
    #131Russian
    -
    13871,190
    #132English
    -
    141110,879
    #134Korean
    -
    1324484
    #143Instruction Following
    -
    13796,310
    #145Longer Query
    -
    13915,217
    #149Expert
    -
    13951,010
    #164Industry Entertainment And Sports And Media
    -
    13284,201
    #168Industry Writing And Literature And Language
    -
    13445,048
    #184Creative Writing
    -
    13163,028

    Related models

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