gpt-6IMAGE
GPT-6 Sol leads Fable 5.1 on AutomationBench
OpenAIDevs said GPT-6 Sol (xhigh) leads Fable 5.1 on AutomationBench, which tests real business workflows across apps, at 88% lower reported cost per task.
OpenAI Developers
@OpenAIDevsArchived 2026.09.23Originally posted 2026.09.23

OpenAI Developers @OpenAIDevsOriginally posted 2026.09.23
On AutomationBench, which measures whether AI models can complete real business workflows across apps, GPT-6 Sol (xhigh) leads Fable 5.1 (max with Opus 5 fallback) with 88% lower reported cost per task. https://t.co/6NrsfCuzBj
x.com/openaidevs/status/2102461480423862692Archived 2026.09.23 10:39