gpt-4

Researchers introduced ProactiveBench, a benchmark testing whether multimodal language models ask for help when visual information is missing. Out of 22 models tested—including GPT-4.1, GPT-5.2, and o4-mini—almost none proactively request clarification, instead hallucinating or refusing to respond. A reinforcement learning approach showed models can be trained to ask for help, improving performance from 17.5% to 37-38%, though significant gaps remain.

OpenAI released Python SDK version 2.23.0 on February 24, 2026, adding support for two new model options in realtime API calls: gpt-realtime-1.5 and gpt-audio-1.5. The minor update primarily focuses on expanding model availability for real-time applications.