lmsys.org(@lmsysorg) 's Twitter Profileg
lmsys.org

@lmsysorg

Large Model Systems Organization. We created Vicuna and Chatbot Arena! Compare 30+ LLMs (GPT-4/Claude/Llamas) side-by-side at https://t.co/IDFeIDIOtm

ID:1641378826537295874

linkhttp://lmsys.org calendar_today30-03-2023 09:56:38

458 Tweets

42,6K Followers

171 Following

lmsys.org(@lmsysorg) 's Twitter Profile Photo

[Update] Evals don't stop on Friday night!

We're very excited to introduce the new Gemini-1.5 Family (Flash, Pro, and Gemini Advanced) to Arena with improved capabilities across the board.

Come chat.lmsys.org and challenge them with your toughest prompts :) leaderboard

account_circle
Raja Biswas(@raja_biswas) 's Twitter Profile Photo

The lmsys.org Kaggle competition seems to be a high signal benchmark to evaluate/study LLM finetuning ideas: avoids early perf saturation, requires knowledge/understanding of diverse domains + strong reasoning capabilities -- LLMs outperforming deberta.
kaggle.com/competitions/l…

account_circle