lmarena top 3
- User
lmarena top 3
Assistant
Based on the latest available information from the LMSys Chatbot Arena leaderboard (around March 26, 2025), here are the top 3 models according to their Arena Elo/Score:
- Gemini-2.5-Pro-Exp-03-25 (by Google) - Arena Elo: 1443[1]
- ChatGPT-4o-latest (2025-03-26) (by OpenAI) - Arena Elo: 1408[1]
- Grok-3-Preview-02-24 (by xAI) - Arena Elo: 1404
Please note:
- The Chatbot Arena leaderboard is based on crowdsourced human preferences from anonymous, randomized battles between models.
- Rankings can change frequently as new models are added and more votes are collected. The specific date associated with the ranking (e.g., March 26, 2025) is important.
- The scores are calculated using the Bradley-Terry model and presented on an Elo-like scale (referred to as "Arena Score"). A higher score indicates better performance based on user votes.
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- gpt-4o-mini-search-previewCompare side by side →
sonar-reasoningCompare side by side →
sonarCompare side by side →
- gpt-4o-search-previewCompare side by side →
sonar-reasoningCompare side by side →
- gpt-4o-search-preview-highCompare side by side →
sonar-pro-highCompare side by side →
- gpt-4o-search-preview-highCompare side by side →
sonarCompare side by side →
- gpt-4o-search-preview-high-locCompare side by side →
sonar-reasoningCompare side by side →
- gpt-4o-mini-search-previewCompare side by side →