Latest baseline
Current eval baseline metrics from latest.json.
| Metric | Value |
|---|---|
| Executions | 154 |
| Passed gates | 145 |
| Avg combined score | 0.923 |
| Spend | $4.99 / $5.00 |
| Single-agent pass | 142/142 |
| Swarm pass | 4/12 |
Swarm timeouts: 8 of 12 swarm runs hit wall-clock limits. Single-agent + tools is the production demo path.