List your company

Story Completion on XStoryCloze 1.0 (test)

71.5XStoryCloze Accuracy (en)TokAlign
43.62850.86458.165.336May 13, 2026

Evaluation results

MethodLinks
TokAlignBackbone=Pythia 6.9B, Tuning Stage=1k steps tuning on multilingual corpus2026.0571.554.548.454.2
TokAlign++Backbone=Pythia 6.9B, Tuning Stage=1k steps tuning on multilingual corpus2026.0571.555.148.254.4
PythiaBackbone=Pythia 6.9B, Tuning Stage=Vanilla (Zero-shot)2026.0570.453.950.353.8
ZeTTBackbone=Pythia 6.9B, Tuning Stage=1k steps tuning on multilingual corpus2026.0570.250.447.753.9
FocusBackbone=Pythia 6.9B, Tuning Stage=1k steps tuning on multilingual corpus2026.0566.848.747.453.9
TokAlign++Backbone=Pythia 6.9B, Tuning Stage=Initialization without any tuning2026.0566.548.446.550.2
TokAlignBackbone=Pythia 6.9B, Tuning Stage=Initialization without any tuning2026.0564.747.747.250.2
TokAlign++Backbone=Pythia 1B, Tuning Stage=1k steps tuning on multilingual corpus2026.0564.651.44853.5
PythiaBackbone=Pythia 1B, Tuning Stage=Vanilla (Zero-shot)2026.0564.348.64852.9
ZeTTBackbone=Pythia 6.9B, Tuning Stage=Initialization without any tuning2026.0564.347.347.649.4
TokAlignBackbone=Pythia 1B, Tuning Stage=1k steps tuning on multilingual corpus2026.0563.449.847.653.2
ZeTTBackbone=Pythia 1B, Tuning Stage=1k steps tuning on multilingual corpus2026.0562.549.447.553.1
TokAlign++Backbone=Pythia 1B, Tuning Stage=Initialization without any tuning2026.056148.147.950.6
FocusBackbone=Pythia 1B, Tuning Stage=1k steps tuning on multilingual corpus2026.056148.347.154.2
TokAlignBackbone=Pythia 1B, Tuning Stage=Initialization without any tuning2026.0559.847.547.450.2
ZeTTBackbone=Pythia 1B, Tuning Stage=Initialization without any tuning2026.0555.847.247.349.4
FocusBackbone=Pythia 6.9B, Tuning Stage=Initialization without any tuning2026.0545.546.745.950.1
FocusBackbone=Pythia 1B, Tuning Stage=Initialization without any tuning2026.0544.747.846.449.4