GPT-6 Luna scores 91.8% on HealthAdminBench at 2% of Astra's cost
thekaransinghal · x · 2026-11-17
OpenAI shared evaluation data for its new model on healthcare admin tasks: on HealthAdminBench, an independent benchmark from Stanford, GPT-6 Luna earned 91.8% of available rubric points versus 94.3% for GPT-6 Astra—despite costing 98% less. Computer use in healthcare will be made widely available.
More from Models
- HSBC cuts Zhipu's price by 2/3rds citing anti-distillation measures by US labs — peterwildeford · 2026-11-17
- OpenAI ships healthcare computer-use agents: 99% of EHR tasks rated safe by physicians — thekaransinghal · 2026-11-17
- Chest X-ray AI flags high fracture risk in 53k-patient NEJM AI study — zakkohane · 2026-11-17
- Model-picker screenshots surface unannounced GPT-6.1, Gemini 4 Hydrogen and Claude Opus 5.5 names — TomLikesRobots · 2026-11-17
- New MKA Benchmark: 200 Expert-Level Multimodal Tasks Across 83 Occupations — osanseviero · 2026-11-17
- OpenAI Brings in Apollo, METR, Transluce and Goodfire for Embedded Safety Assessments — OpenAI · 2026-11-17