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

  • LLMs
  • Source: The Decoder
  • Published: 2026-04-25
  • Signal score: 3
  • 128 sources

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.

More LLMs stories

  1. OpenAI acquires presentation startup NextSlide

    TechCrunch · 2026-08-08

    NextSlide says its team members are now working on ChatGPT.

  2. Claude Vs ChatGPT: How These AI Assistants Differ

    Engadget · 2026-08-08

    In a practical breakdown of how Claude and ChatGPT AI models differ, one tends to fall short when it comes to quality responses and overall user experience.

  3. Anthropic sets Claude Code to Auto Mode by default to protect developers from bad approvals

    The Decoder · 2026-08-08

    Starting August 14, Anthropic will make Auto Mode in Claude Code the default for Pro, Max, and Team plans. The company says it's safer.

  4. Responding to the next frontier of critical cyber capabilities

    OpenAI Blog · 2026-08-07

    OpenAI is sharing preliminary cybersecurity evaluations for Astra and the steps we’re taking to strengthen safeguards and security controls.

  5. OpenAI says it slowed Astra model development over security concerns

    TechCrunch · 2026-08-07

    OpenAI said this model, which is still in development, reached its "critical cybersecurity threshold," meaning it could independently identify and carry out cyberattacks against

  6. Presentation: Keeping ChatGPT Fast as AI Development Accelerates

    InfoQ · 2026-08-08

    Martin Spier explains how agentic workflows dramatically increase code change volume at OpenAI. He d