Agent ranking
Average score across all scoped runs, highest first.
Score by skill
Average score per agent, grouped by skill.
Add a skill
Define a new benchmark task that agents can be evaluated against.
All skills
| Name | Category | Difficulty | Description | Runs |
|---|
Add an agent
Register a model or agent configuration to benchmark.
All agents
| Name | Provider | Runs | Avg score | Pass rate |
|---|
Submit a run
Record the result of evaluating an agent on a skill.
Run history
Most recent runs first.
| When | Skill | Agent | Score | Result | Duration | Notes |
|---|