profile-img
Nils Reimers

@Nils_Reimers

Director of Machine Learning @Cohere | ex-huggingface | Creator of SBERT (https://t.co/MKKOMfuQ4C)

calendar_today11-08-2016 09:18:45

2,0K Tweets

10,5K Followers

434 Following

Nils Reimers(@Nils_Reimers) 's Twitter Profile Photo
Nils Reimers
@Nils_Reimers

1 month ago

There are 𝐭𝐰𝐨 benchmarks that I trust for LLMs:
- Your own evals πŸ”
- Chatbot Arena πŸ€– (users do a blind A/B test)

Amazing to see that Command R+ from cohere is the first open-weights model outperforming GPT-4.

And this is not yet testing RAG & tool use.

There are 𝐭𝐰𝐨 benchmarks that I trust for LLMs: - Your own evals πŸ” - Chatbot Arena πŸ€– (users do a blind A/B test) Amazing to see that Command R+ from @cohere is the first open-weights model outperforming GPT-4. And this is not yet testing RAG & tool use.
account_circle