lmarena top 3
- User
lmarena top 3
Assistant
To find the top three models in the LMArena (Chatbot Arena), we can refer to recent updates and leaderboards available from various sources. However, the most current leaderboard might not be directly accessible due to server issues or updates. Here's a summary based on available information:
-
Vicuna-13B: This model, fine-tuned from LLaMA on user-shared conversations by LMSYS, has been a top performer in the past, with an Elo rating of 1169 as of early May 2023[1].
-
Koala-13B: Developed by BAIR for academic research, this model has also been highly ranked, with an Elo rating of 1082 during the same period[1].
-
Oasst-Pythia-12B: An Open Assistant by LAION, this model has shown strong performance with an Elo rating of 1065[1].
For the most recent rankings, it's advisable to check the official LMArena website or related platforms like OpenLM.ai once they are updated and accessible[2][4].
Additionally, other models like DeepSeek-R1 and Gemma-3-27B-it have shown high performance in broader benchmarks, but their specific rankings in LMArena might vary[2].
-
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 →
- 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 →