Board
Tasks, submitters and reviewers
Claims, open pull requests and merged tasks across every project. Each card shows which model built the task, who submitted it, how frontier models did, and where its review stands. Review gives you one command that opens the run viewer, results and check report in your browser, a prompt for your own agent, and the commands to record your verdict.
- Tasks
- 0
- Contributors
- 0
- Projects covered
- 0/15
- Merged
- 0
People
Tasks each person submitted, by area, and the pull request reviews they gave. Choose a name or a number to see those tasks on the board above. Reviews are how people shape the benchmark.