| Benchmark | Model | Rank | Results |
|---|---|---|---|
| text-summarization-on-dialogsum | InstructDS | #1 | Rouge1: 47.8Rouge2: 22.2RougeL: 39.4 |
| text-summarization-on-samsum-corpus | InstructDS | #1 | ROUGE-1: 55.3ROUGE-2: 31.3ROUGE-L: 46.7BertScoreF1: 55.5 |
| machine-reading-comprehension-on-dream | InstructDS | #2 | Accuracy: 65.9 |