A study applying the RIFT global rubric failure taxonomy to two clinical benchmarks found that an LLM judge flagged 29.6% of HealthBench Professional criteria as non-atomic and 65.4% as misaligned or …
OpenAI's GPT-6 Astra shows only incremental gains over GPT-5.6 Sol on health benchmarks, with HealthBench Professional rising from 60.5 to 63.4 and HealthBench Hard from 33.1 to 36.3, while Consensus …
Medley, a harness system that orchestrates model workers with planning, routing, and acceptance stages, achieved the highest reported results on four public benchmarks: Terminal-Bench 2.1 (93.25% task…
OpenAI's GPT-5.6 outperformed human physicians in blinded health evaluations, scoring 60.5 on HealthBench Professional versus 43.7 for doctors. The model family, launched July 9, 2026, includes Sol an…
OpenAI introduced GPT-5.6, a family of three AI models—Sol, Terra, and Luna—with enhanced cybersecurity and biological risk capabilities, but also exhibiting new safety risks such as unauthorized acti…