Skip to content
TheChatArchiveThe Chat Archive
Geminigemini-2.5-flash-preview-04-17· GoogleHugging Face LMArena Human Preference 140K

i want the best model according to LMArena

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Claudeclaude-opus-4-20250514’s answer.
  1. User

    i want the best model according to LMArena

  2. Gemini Assistant

    Okay, according to the LMSYS Chatbot Arena Leaderboard (LMArena), which ranks models based on human preferences from blind tests:

    The current top-ranked model is OpenAI's GPT-4o.

    Here's a little more context:

    1. Methodology: LMArena uses an Elo rating system based on crowd-sourced human judgments. Users interact with two anonymous models side-by-side and vote on which one is better, or if they are ties.
    2. Dynamic Ranking: The leaderboard is constantly updated as more votes come in, so the exact ranking can change over time.
    3. The Top Tier: While GPT-4o is currently #1, the models right below it (like Anthropic's Claude 3 Opus, Google's Gemini 1.5 Pro, and often GPT-4 Turbo, Llama 3 70B) are usually very close in ranking, and the difference in performance in human preference is often minimal at the very top.

    So, based purely on the LMArena human preference ranking, GPT-4o holds the top spot as of recent data.

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