| Tool Version Sen Tok Model Tokens/ms effi1x - 100 runs Tokens/ms effi10x - 100 runs |
| KorAP-Tokenizer 72.90 199.28 |
| Datok x x datok 837.89 2478.71 |
| x x matok 1371.19 2976.80 |
| BlingFire 0.1.8 x wbd.bin 431.92 1697.73 |
| x sbd.bin 417.10 1908.87 |
| Cutter 2.5 x x 0.38 |
| JTok 2.1.19 31.19 117.22 |
| OpenNLP x Simple 290.71 1330.23 |
| x Tokenizer 74.65 145.08 |
| x SentenceD 247.84 853.01 |
| SoMaJo x x P=1 8.15 8.41 |
| x x P=8 27.32 39.91 |
| SpaCy x Tokenizer 19.73 44.40 |
| x Sentencizer 16.94 |
| x Statistical 4.90 |
| x Dependency 2.24 |
| Stanford x 75.47 156.24 |
| x x T,S,M 46.95 91.56 |
| Syntok x segmenter 59.66 61.07 |
| x tokenizer 103.90 108.40 |
| Waste 2.0.20-1 x x 141.07 144.95 |
| Elephant x 8.57 8.68 |
| TreeTagger x 69.92 72.98 |
| Deep-EOS x bi-lstm-de 0.25 |
| x cnn-de 0.27 |
| x lstm-de 0.29 |
| NNsplit x 0.90 |