gpt-6IMAGE
GPT-6 Sol 在 AutomationBench 领先 Fable 5.1
OpenAIDevs 称在真实业务流程的 AutomationBench 上，Sol (xhigh) 领先 Fable 5.1，单任务成本低 88%。
OpenAI Developers
@OpenAIDevs2026.09.23收录原推发布于 2026.09.23
OpenAI Developers @OpenAIDevs原推发布于 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/2102461480423862692采集于 2026.09.23 10:39