AI news story

An AI model programmed nonstop for 19 days on a single MirrorCode task that cost $2,600 to run

Epoch AI's new MirrorCode benchmark tests whether AI models can recreate complete programs without access to the original code. Claude Opus 4.7 leads with a 56 percent solve rate, rebuilding a 16,000-line toolkit in just 14 hours. But every model tes

  • LLMs
  • Source: The Decoder
  • Published: 2026-06-26
  • Signal score: 4
  • 21 sources

Editor's take

Epoch AI's MirrorCode benchmark reveals Claude Opus 4.7's impressive ability to reconstruct complex software from scratch, achieving a 56% success rate on a 16,000-line program in 14 hours. This signifies a significant leap in AI's capacity for code synthesis and understanding, directly impacting software development workflows and potentially democratizing complex programming tasks. The accuracy and speed demonstrated by Opus, even in early testing stages, suggest a future where AI can significantly augment human coding efforts.

The implications extend to how we design and deploy AI systems, particularly in domain-specific tasks requiring deep contextual understanding. While Claude Opus leads, the performance of other models on MirrorCode will be crucial for understanding the breadth of this capability across different architectures. Future developments will likely focus on improving efficiency, reducing computational cost, and expanding the complexity of programs these models can tackle, pushing the boundaries of AI-driven software engineering.

Signal score: 4

This event was corroborated by 21 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