GPT-6 Astra Tops GDP.pdf Long-Document Reasoning Benchmark at 33.2% All-Pass Rate

ArtificialAnlys · x · 2026-09-05

Artificial Analysis shared per-model GDP.pdf results: OpenAI's GPT-6 Astra leads at 33.2%, with GPT-5.6 Sol at 28.2% and Claude Fable 5.1 at 26.2%. Created by @HelloSurgeAI, GDP.pdf tests single-turn professional document reasoning across 100 PDFs and ten domains, requiring models to synthesize evidence from 4,592 pages of text, tables, charts, and footnotes, graded against 1,275 expert-authored atomic criteria with an all-pass headline metric.

Related event: Artificial Analysis Releases Intelligence Index v4.2; GPT-6 Astra Tops GDP.pdf Benchmark(6 posts)→

Original post →

More from Models

Models channel →