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 · Non English

    Meta: Llama 3.2 3B Instruct

    Released Sep 25, 2024
    meta-llama/llama-3.2-3b-instruct
    text→text
    Set alert
    Ranked in:Text
    Try it on:
    OOpenRouter

    Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...

    Best overall rank
    #322
    ▼ 1 vs 7d ago
    Total arena votes
    46,091
    Across 24 (subset, category) entries
    Providers on OR
    2
    Parasail + others
    First seen
    2026-05-08
    61 days tracked

    Trend

    Pricing

    Per token

    Input (per 1M)
    $0.050
    Output (per 1M)
    $0.330

    Capabilities

    Modality
    text->text
    Context
    131K tokens
    Tokenizer
    Llama3
    Knowledge cutoff
    2023-12-31
    Max output
    131K tokens
    Moderation
    Unmoderated
    Hugging Face
    meta-llama/Llama-3.2-3B-Instruct
    Supported parameters
    frequency_penalty
    logit_bias
    logprobs
    max_tokens
    min_p
    presence_penalty
    repetition_penalty
    seed
    stop
    structured_outputs
    temperature
    top_k
    top_logprobs
    top_p

    Providers

    ProviderRegion / TagContextInput/MOutput/MUptime 1dLatencyQuantCache
    Parasailparasail/bf16131K$0.050$0.33099.97%-
    bf16
    -
    Cloudflarecloudflare80K$0.051$0.33599.64%---

    Per-category ranks

    Text

    RankCategoryVariantTrendEloVotes
    #258German
    -
    1110232
    #290Expert
    -
    1175499
    #296Industry Medicine And Healthcare
    -
    1202441
    #301Industry Mathematical
    -
    1174980
    #304English
    -
    12244,157
    #304Math
    -
    11651,136
    #308Hard Prompts English
    -
    12081,377
    #309Multi Turn
    -
    11481,299
    #310Industry Entertainment And Sports And Media
    -
    11411,149
    #311Industry Legal And Government
    -
    1188506
    #312Creative Writing
    -
    11441,070
    #315Chinese
    -
    1128721
    #317Longer Query
    -
    11581,046
    #318Industry Life And Physical And Social Science
    -
    11851,355
    #319Industry Writing And Literature And Language
    -
    11422,118
    #319Instruction Following
    -
    11453,171
    #322Hard Prompts
    -
    11672,216
    #322Industry Business And Management And Financial Operations
    -
    11461,012
    #322Overall
    -
    11667,936
    #325Exclude Ties
    -
    10095,442
    #327Industry Software And It Services
    -
    11742,165
    #328Coding
    -
    11761,351
    #330Russian
    -
    1004933
    #331Non English
    -
    10873,779

    Related models

    Meta: Llama 3.2 3B Instruct (free)meta-llama/llama-3.2-3b-instruct:free