• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Artificial Analysis Posts GDP.pdf Model Leaderboard

    Artificial Analysis shares results from the GDP.pdf document reasoning benchmark created by HelloSurgeAI.

    AA
    2 Sources, 26d ago, first seen 26d ago

    TLDR

    Artificial Analysis posted results from the GDP.pdf evaluation on X. The benchmark created by HelloSurgeAI tests single-turn professional document reasoning across 100 PDFs in ten domains that together contain 4,592 pages. The company states that OpenAI leads with GPT-6 Astra at 33.2% and GPT-5.6 Sol at 28.2%, followed by Claude Fable 5.1 at 26.2%. The posts include two-panel charts and a grid of bar charts titled Intelligence Evaluations.

    Combined views

    37.8K

    2 Sources, first seen 26d ago

    Combined views

    37.8K

    2 Sources, first seen 26d ago

    141 likes
    141 likes
    3 comments
    19 saves
    1 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    3 comments
    19 saves
    1 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    @ArtificialAnlysOpenAI leads GDP.pdf with GPT-6 Astra at 33.2% and GPT-5.6 Sol at 28.2%, followed by Claude Fable 5.1 at 26.2%. Created by @HelloSurgeAI, GDP.pdf evaluates single-turn professional document reasoning across 100 PDFs and ten domains. Models must synthesize evidence distributed across 4,592 pages, including text, tables, charts, footnotes, and exclusions. Responses are graded against 1,275 expert-authored atomic criteria; the headline All-pass Rate credits a task only when every criterion is satisfied.

    2 Sources

    @ArtificialAnlysOpenAI leads GDP.pdf with GPT-6 Astra at 33.2% and GPT-5.6 Sol at 28.2%, followed by Claude Fable 5.1 at 26.2%. Created by @HelloSurgeAI, GDP.pdf evaluates single-turn professional document reasoning across 100 PDFs and ten domains. Models must synthesize evidence distributed across 4,592 pages, including text, tables, charts, footnotes, and exclusions. Responses are graded against 1,275 expert-authored atomic criteria; the headline All-pass Rate credits a task only when every criterion is satisfied.