BenchmarkChatTS
ChatTS
An evaluation task oriented toward conversational understanding and alignment over time series, testing a model's numerical accuracy on multivariate time series. It measures whether a model can correctly interpret and respond to queries grounded in temporal data.
Timeline (last 90 days)
Oct 16
The dual-view model achieved a numerical accuracy of 86.8% on the multivariate ChatTS alignment task.
Unverified50%