Skip to content
TheChatArchiveThe Chat Archive
gpt-4o-search-preview-high-loc· OpenAIHugging Face LMArena Search Arena 24K

what is considered the smartest llm as of 3/29/25.

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with gpt-4o-search-preview-high-loc’s answer.
  1. User

    what is considered the smartest llm as of 3/29/25.

  2. Assistant

    As of March 29, 2025, OpenAI's o1 model is widely regarded as the most advanced large language model (LLM) available. It achieved a score of 91.8% on the Massive Multitask Language Understanding (MMLU) benchmark, which assesses models across a diverse range of subjects[1].

    Following closely, DeepSeek's R1 model scored 90.8% on the MMLU benchmark. DeepSeek has rapidly emerged as a significant player in the AI landscape, offering models that compete with Western counterparts while maintaining lower operational costs[2].

    Anthropic's Claude 3.5 Sonnet also demonstrates strong performance, with an MMLU score of 88.7%. This model is noted for its advanced reasoning capabilities and is a preferred choice for tasks requiring deep understanding and nuanced responses[3].

    These models represent the forefront of LLM development as of late March 2025, each excelling in various aspects of language understanding and generation.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.