FactStream

GPT-5.6 Sol Benchmark Performance

OpenAI's GPT-5.6 Sol reportedly achieved a score of 53.6 on the 'Agents’ Last Exam' benchmark, surpassing the results of Anthropic's Claude Fable 5.

Aggregated from 1 sources · Updated 30 Jul 2026, 08:53 UTC (UTC)

Share

Coverage Balance

1 sources
Center 100%

Blindspot Alert: Center Gap

This event is primarily covered by one side of the political spectrum. Niche or counter-narrative facts may be underrepresented.

Facts (1)

  • AttributionNiche Signal

    OpenAI's GPT-5.6 Sol reportedly outperformed Claude Fable 5 on the 'Agents’ Last Exam' benchmark, scoring 53.6 compared to Fable 5's lower results.

We'll extract atomic facts from your source and add them below for cross-checking. Single-source facts surface as Emerging or Unverified.