Leaderboard
The overall model score on the leaderboard is calculated based on the average of all metrics for the task. The overall total is the average for all tasks, the private total is based on private tests only.
The MERA SWE leaderboard for dynamic evaluation of driving models is available on a separate website at link
Select tasks
All tasks
{{ task.title }}
{{ task.leaderboard_description }}
Select programming languages
All languages
{{ language.title }}
Filters
Reset
Main tasks
All tasks
{{ task.title }}
{{ task.leaderboard_description }}
Select programming languages
All languages
{{ language.title }}
Model, team
Total overall
Private total
{{ i + 1 }}
{{ submit.name }}
{{ transformSize(submit.size) }}
{{ submit.team_name }}
{{ submit.score }}
{{ submit.private_score }}
| {{ task.title }} |
|---|
| {{ getTaskScore(submit, task) }} |
There are no suitable results
mera@a-ai.ru
GitHub
hugging face