Rohan Paul

@rohanpaul_ai

Meta’s Muse Spark 1.3 Max is Code Arena’s highest-scoring WebDev model below $5 per mn tokens. It scores 1,650 at a blended $3.50 per million tokens, placing #8 overall. Those scores reflect evaluations of generated web applications, including functionality, usability and how closely they follow the request.
打开原帖#511482
  1. Research

    Rohan Paul: The paper shows that refreshing an agent's memory does not refresh its plan, so the plan should be checked again before execution.
  2. Research

    Rohan Paul: https://www.reuters.com/world/asia-pacific/openai-says-working-with-samsung-next-generation-chips-deepening-cooperation-2026-09-09/
  3. Research

    Rohan Paul: OpenAI is jointly researching and producing new AI chips with Samsung Electronics, its Korea office said