AI news story
GPT-5.5 tops benchmarks but still hallucinates frequently and costs 20 percent more over the API
GPT-5.5 pushes OpenAI back to the top of the AI benchmarks. The price went up, but it still looks like the best bang for your buck among proprietary models. The article GPT-5.5 tops benchmarks but still hallucinates frequently and costs 20 percent mo
Editor's take
OpenAI's latest iteration, GPT-5.5, has reclaimed the top spot on key LLM benchmarks, surpassing competitors like Google's Gemini Ultra and Anthropic's Claude 3 Opus. This performance boost, however, comes with a 20% API price increase and persistent hallucination issues, a known challenge for even the most advanced large language models.
The continued benchmark leadership underscores OpenAI's ongoing dominance in raw capability and reasoning, making it the default choice for many developers despite the cost. The persistent hallucination problem, however, highlights the fundamental limitations of current transformer architectures and the ongoing need for robust fact-checking mechanisms, even as models become more powerful.
Future developments to monitor include whether OpenAI can significantly reduce hallucination rates in subsequent releases or if competitors will leverage this weakness to gain market share, potentially through more reliable, albeit slightly less performant, offerings. The sustained high cost also raises questions about broader market accessibility and the viability of enterprise-grade AI deployments reliant on expensive proprietary APIs.
Signal score: 3
This event was corroborated by 128 independent sources. The signal score weighs cross-source corroboration, recency, source weight and topic salience. How we rank stories.
Original reporting
This story summarises reporting published by The Decoder. Read the original article at The Decoder.