Sentence Completion on StoryCloze
90.8AccuracyFine-tuned
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Fine-tunedBackbone=T5-large2026.06 | 90.8 | — | |
| ReTeXBackbone=T5-large, Merging Strategy=Dynamic model merging2026.06 | 90.3 | 99.4 | |
| Task ArithmeticBackbone=T5-large, Merging Strategy=Static model merging2026.06 | 86.4 | 95.2 | |
| Twin-MergingBackbone=T5-large, Merging Strategy=Dynamic model merging2026.06 | 85.6 | 94.3 | |
| TIES-MergingBackbone=T5-large, Merging Strategy=Static model merging2026.06 | 83.6 | 92.1 | |
| MoW-MergingBackbone=T5-large, Merging Strategy=Dynamic model merging2026.06 | 83.1 | 91.5 | |
| AdaMergingBackbone=T5-large, Merging Strategy=Static model merging2026.06 | 82.1 | 90.4 | |
| Consensus TABackbone=T5-large, Merging Strategy=Static model merging2026.06 | 79.9 | 88 | |
| WEMoEBackbone=T5-large, Merging Strategy=Dynamic model merging2026.06 | 79.6 | 87.7 | |
| DaWinBackbone=T5-large, Merging Strategy=Dynamic model merging2026.06 | 73.2 | 80.6 | |
| Weight AveragingBackbone=T5-large, Merging Strategy=Static model merging2026.06 | 53.7 | 59.1 |