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 · Overall

    Qwen: Qwen3 Next 80B A3B Thinking

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

    Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic...

    Best overall rank
    #153
    ▼ 1 vs 7d ago
    Total arena votes
    74,948
    Across 27 (subset, category) entries
    Providers on OR
    5
    AtlasCloud + others
    First seen
    2026-05-08
    45 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.098
    Output (per 1M)
    $0.780

    Capabilities

    Modality
    text->text
    Context
    262K tokens
    Tokenizer
    Qwen3
    Knowledge cutoff
    2025-09-30
    Max output
    33K tokens
    Moderation
    Unmoderated
    Hugging Face
    Qwen/Qwen3-Next-80B-A3B-Thinking
    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
    AtlasCloudatlas-cloud/fp8262K$0.150$1.50100.00%-
    fp8
    -
    Novitanovita/bf16131K$0.150$1.5099.89%-
    bf16
    -
    Nebiusnebius/fp8128K$0.150$1.2099.28%-
    fp8
    -
    Googlegoogle-vertex/global262K$0.150$1.2099.07%---
    Alibabaalibaba131K$0.098$0.78098.65%---

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #128German
    thinking
    1367285
    #130Japanese
    thinking
    1296180
    #132Chinese
    thinking
    1413715
    #133Korean
    thinking
    1319332
    #135Math
    thinking
    1390828
    #138Industry Mathematical
    thinking
    1388668
    #148Coding
    thinking
    14212,676
    #148English
    thinking
    13876,636
    #148Industry Software And It Services
    thinking
    14104,837
    #149Expert
    thinking
    1385620
    #150Industry Medicine And Healthcare
    thinking
    1393720
    #153French
    thinking
    1366195
    #153Instruction Following
    thinking
    13593,517
    #153Overall
    thinking
    137013,693
    #154Exclude Ties
    thinking
    13379,759
    #155Hard Prompts
    thinking
    13846,691
    #155Industry Business And Management And Financial Operations
    thinking
    13672,497
    #155Spanish
    thinking
    1351399
    #156Hard Prompts English
    thinking
    13973,497
    #157Longer Query
    thinking
    13702,835
    #158Russian
    thinking
    1353750
    #159Industry Life And Physical And Social Science
    thinking
    13802,124
    #164Multi Turn
    thinking
    13512,296
    #166Creative Writing
    thinking
    13241,797
    #166Industry Writing And Literature And Language
    thinking
    13393,078
    #171Industry Entertainment And Sports And Media
    thinking
    13172,454
    #175Industry Legal And Government
    thinking
    1360869