Please check the Getting Started page for instructions on how to make a submission to this leaderboard.
Global
Only submissions evaluated on at least 5 core tasks (Dialogue, Summarization, Intent Detection, Stance Classification and Safety Detection) are shown in the Global Leaderboard.
CRoW Score [-MT] = Average Score across all except Machine Translation tasks
SA = Situational Accuracy
| Contributor |
Model |
Model Size |
CRoW Score [-MT]
(macro-F1) |
CRoW Score [-MT]
(SA) |
CRoW Score
(macro-F1) |
CRoW Score
(SA) |
By Task
Open-domain Dialogue
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
Dialogue Summarization
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
Intent Detection
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
Safety Detection
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
Stance Classification
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
Machine Translation
Only submissions evaluated on all MT tasks (zh-en, en-de, en-fr, en-ru) are shown in this leaderboard.
| Contributor |
Model |
Model Size |
Macro-F1 |
SA |
Machine Translation (zh-en)
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
Machine Translation (en-de)
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
Machine Translation (en-fr)
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
Machine Translation (en-ru)
| Contributor |
Model |
Model Size |
Date |
Macro-F1 |
SA |
