These 7 AI models just overtook ChatGPT in a new study

A recent analysis from British research firm Prolific has stirred waves in the AI community, revealing that OpenAI’s ChatGPT has been outperformed by several emerging models. Since its launch in late 2022, ChatGPT quickly became a dominant player in the generative AI chatbot market. However, this new study positions it at an unexpected 8th place among AI models, trailing behind competitors like Gemini, Grok, Claude, and Mistral. Prolific developed a benchmark called "Humaine" to evaluate AI performance based on natural human interactions rather than traditional metrics that may not resonate with everyday users. The company argues that current evaluation methods often prioritize accuracy on specialized datasets, which can create a disconnect between what is optimized and what users actually value. They emphasize the importance of designing evaluations with scientific rigor to avoid biases that might favor tech-savvy participants. According to the Humaine study, the top AI models are ranked as follows: 1. Gemini 2.5 Pro (Google), 2. DeepSeek v3 (DeepSeek), 3. Magistral Medium (Mistral), 4. Grok 4 (xAI), 5. Grok 3 (xAI), 6. Gemini 2.5 Flash (Google), 7. DeepSeek R1 (DeepSeek), 8. ChatGPT-4.1 (OpenAI), 9. Gemma (Google), and 10. Gemini 2.0 Flash (Google). Interestingly, the study was conducted before the release of Google’s Gemini 3 Pro and the latest Grok models from xAI. Given Gemini 2.5 Pro's strong performance across various assessments since its launch, its leading position in this ranking is not surprising. However, ChatGPT's placement outside the top five raises questions about its standing in the rapidly evolving AI landscape. While researchers did not provide specific reasons for ChatGPT’s lower ranking, they highlighted that Google’s Gemini 2.5 Pro consistently claimed the top spot for the “Overall Winner” metric.