The daily score calculation scales exponentially with the number of models and benchmarks, and is likely the cause of the daily "slow loading" we are currently seeing (previously resulting in regular downtime before we upgraded the web instance size). Optimizing and/or offloading this calculation (e.g. to an ephemeral EC2 instance) will hopefully resolve these issues.
The daily score calculation scales exponentially with the number of models and benchmarks, and is likely the cause of the daily "slow loading" we are currently seeing (previously resulting in regular downtime before we upgraded the web instance size). Optimizing and/or offloading this calculation (e.g. to an ephemeral EC2 instance) will hopefully resolve these issues.