GPT-5.6 Health Capabilities and Cost-Effectiveness Improve
mckbrando · x · 2026-07-11
A circulated update regarding OpenAI claims that GPT-5.6 has made significant progress in the healthcare domain, alongside improvements in performance and cost.
Key points:
- At its lowest reasoning intensity, the smaller model GPT-5.6 Luna outperforms the maximum reasoning intensity of GPT-5.5, yet costs only 1/25 of the price.
- The larger model GPT-5.6 Sol also reaches a new high in cost performance.
- In a health task evaluation, doctors concluded in a blind comparison that GPT-5.6's answers had fewer issues than those written by human doctors.
- The evaluation covered recent patient-side and clinical-side tasks that OpenAI models still found difficult. Control answers were written by specialists with internet access and unlimited time before being compared blindly.
More from Models
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27