NLP
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
NLP Standard Suite
2.278CE Loss
18
NLP
95.96Node Significance
15
NLP
0.007Cost per 1K Requests ($)
15
NLP
49.25Sycophancy Preference
10
NLP variable-length
5.03Throughput (M tok/s)
4
Loading the SOTA2 catalog…