Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-task Evaluation Suite

Benchmarks

Task NameDataset NameSOTA ResultTrend
Aggregate PerformanceMulti-task Evaluation Suite
Average Performance49
21
DecodingMulti-task Evaluation Suite Llama-3.2-1B (test)
MT Throughput (token/s)394.81
6
Showing 2 of 2 rows