Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sentence Completion on StoryCloze
Loading...
90.8
Accuracy
Fine-tuned
52.216
62.233
72.25
82.267
Jun 25, 2026
Accuracy
Normalized Accuracy
Updated 29d ago
Evaluation Results
Method
Method
Links
Accuracy
Normalized Accuracy
Fine-tuned
Backbone=T5-large
2026.06
90.8
-
ReTeX
Backbone=T5-large, Mer...
2026.06
90.3
99.4
Task Arithmetic
Backbone=T5-large, Mer...
2026.06
86.4
95.2
Twin-Merging
Backbone=T5-large, Mer...
2026.06
85.6
94.3
TIES-Merging
Backbone=T5-large, Mer...
2026.06
83.6
92.1
MoW-Merging
Backbone=T5-large, Mer...
2026.06
83.1
91.5
AdaMerging
Backbone=T5-large, Mer...
2026.06
82.1
90.4
Consensus TA
Backbone=T5-large, Mer...
2026.06
79.9
88
WEMoE
Backbone=T5-large, Mer...
2026.06
79.6
87.7
DaWin
Backbone=T5-large, Mer...
2026.06
73.2
80.6
Weight Averaging
Backbone=T5-large, Mer...
2026.06
53.7
59.1
Feedback
Search any
task
Search any
task