SYLIN

GDPval

by OpenAI · Benchmark · Text & code

Knowledge-work benchmark across finance, data science, biotech and marketing; GPT models beat Claude on it

Evidence

  1. Sep 27
    Grok 4.7 beats GPT-6 Astra on GDPval, a few points below Fable 5.1
  2. Jul 25
    Cited by Anthropic as a benchmark where Opus 5 sets a new state of the art

Alternatives

GLMOn agentic coding benchmarks incl. Terminal-Bench, Agents' Last Exam, AutomationBench, GDPval it sits at or near the top of open models, near closed frontier