Skip to content
TheChatArchiveThe Chat Archive
Geminigemini-2.5-pro-exp-03-25-grounding· GoogleHugging Face LMArena Search Arena 24K

lmarena top 3

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Geminigemini-2.5-pro-exp-03-25-grounding’s answer.
  1. User

    lmarena top 3

  2. Gemini Assistant

    Based on the latest information from the LMSYS Chatbot Arena leaderboard, which ranks large language models based on crowdsourced human evaluations using an Elo rating system, here are the top 3 models as of late March 2025:

    1. Gemini-2.5-Pro-Exp-03-25 (Google): This experimental model currently holds the top spot with an Arena Elo score of 1443. It debuted at the top "by a significant margin" according to one source.
    2. Grok-3-Preview-02-24 (xAI): This preview model ranks second with an Arena Elo score of 1404.
    3. chocolate (Early Grok-3) (xAI): An earlier version of Grok-3, ranks very closely behind the preview version, with an Arena Elo score of 1402. Alternatively, some views might place GPT-4.5-Preview (OpenAI) at #3 or tied for #2 depending on confidence intervals, as it has a score of 1398.

    It's worth noting that these rankings are based on over 2.8 million votes collected via anonymous, randomized battles on the Chatbot Arena platform. The leaderboard is frequently updated.[[1]]

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