Unknown Language Performance

Unknown Language Scores by Model

Average of 2000 bootstraps. 95% CI are shown.

Select at least one model to display.

Model Size: ≤200B

Open models only

Unknown Language Competency & Task Scores

Average of 2000 bootstraps. 95% CI are shown.

Model
MY)发布,以促进持续评估。
No records

Model Size: ≤200B

Open models only