Spaces:
Running
on
CPU Upgrade
Request for LLM Leaderboard Update Schedule
Hi, I appreciate the valuable work on maintaining this leaderboard. I noticed that our team has submitted results for evaluation a while ago, and I was wondering if there is an estimated timeline for when the next leaderboard update will be released.
We understand that thorough evaluation takes time to ensure quality and fairness. However, it would be helpful if you could share:
The current status of pending submissions
The approximate schedule for the next update
Any potential bottlenecks in the evaluation process
This information would help us better coordinate our research timeline and future submissions. Thank you for your continuous efforts in maintaining this important benchmark for the LLM community.
Hi,
Thank you for your interest in our tool! We’re currently working on several improvements for the leaderboard. At present, we’ve identified some bottlenecks that involve challenges accessing computing resources and ensuring the stability of our proposed metrics.
The next update is set to take place during the second week of April. As part of this process, we plan to re-run all submitted models to verify their replicability once again.
Once again, thank you for your patience as we work on enhancing the tool. We’ll keep you informed about any further developments!