OpenAI’s GPT-5.5 achieved a 93/100 score in ZDNET’s 10-part evaluation, showing strong performance in coding, reasoning, and creative writing. The model excelled in tasks from algorithmic ...
Hosted on MSN
Claude Opus 4.7 tops GPT-5.5 in reasoning tests
Anthropic’s Claude Opus 4.7 has outperformed OpenAI’s new GPT-5.5 in a series of challenging reasoning and logic tests, despite GPT-5.5’s strong performance in agentic coding benchmarks. The ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results