OpenAI发了GPT-5.6，医生写回答都写不过它，成本还更低，医疗AI又进步了一大截
OpenAI发布GPT-5.6系列，在医疗任务中表现优于医生。最小变体GPT-5.6 Luna在最低推理努力下即超越GPT-5.5最高推理努力，成本降低25倍。最大变体GPT-5.6 Sol创下新标杆。研究收集了患者和临床医生两类任务，由专科医生花费无限时间并联网撰写回答，再由另一些医生盲评。在20000次轴评级（准确性、沟通、完整性、指令遵循、健康决策有用性）中，所有GPT-5.6变体在完美率上显著超过医生。
"physicians found fewer flaws in GPT-5.6 responses than physician-written responses."
"physicians found fewer flaws in GPT-5.6 responses than physician-written responses." Karan Singhal @thekaransinghal ♥️ GPT-5.6 is a major step forward for health, both at the frontier and at cost. These models push the frontier of performance per dollar, bringing the best health intelligence to all. The smallest variant, GPT-5.6 Luna, evaluated at the lowest reasoning effort, outperforms GPT-5.5 at the highest reasoning effort–despite costing 25x less. The largest variant, GPT-5.6 Sol, sets a new high bar at cost. Another especially cool result: physicians found fewer flaws in GPT-5.6 responses than physician-written responses. We collected diverse tasks that remain difficult for recent OpenAI models, across patient-facing and clinician-facing use cases. We asked speciality-matched physicians to write responses to these tasks with unlimited time and web access. We then asked other physicians to compare responses side-by-side, blinded to their source. Physicians were asked to comment on areas of improvement across five axes: accuracy, communication, completeness, instruction following, and health decision helpfulness. We then reported the fraction of responses across sources rated perfectly across all axes, across 20,000 total axis ratings. GPT-5.6 Sol appeared strongest, although all GPT-5.6 models performed significantly better than physicians. 🔗 View Quoted Tweet 💬 143 🔄 62 ❤️ 1051 👀 137339 📊 165 ⚡