OpenAI has released GPT-5.5, a major upgrade to its AI model lineup, targeting coding, computer use, and research tasks. The model introduces native computer navigation, a 1.1 million-token context ...
New benchmark results for ChatGPT 5.5 highlight strong performance in tool coordination but weaker results on complex, multi-step software engineering tasks. Tests using Terminal-Bench 2.0 and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results