RUNS · 12 recorded
Run history
agent-harness
| # | Eval | Model | Mode | Result | Score | Judges | Duration | Time | |
|---|---|---|---|---|---|---|---|---|---|
| #18 | add-dashboard-route | claude-sonnet-4-6 | inject | PASS | 1.00 | corr5code5conv5 | 30s | 4/8/2026 | |
| #17 | add-db-column | claude-sonnet-4-6 | inject | PASS | 1.00 | corr5code5conv5 | 18s | 4/8/2026 | |
| #16 | add-mcp-tool | claude-sonnet-4-6 | inject | PASS | 1.00 | corr5code5conv5 | 43s | 4/8/2026 |
homelab
| # | Eval | Model | Mode | Result | Score | Judges | Duration | Time | |
|---|---|---|---|---|---|---|---|---|---|
| #15 | add-deployment-repo-app | claude-sonnet-4-6 | inject | PASS | 1.00 | Conv5 | 23s | 4/8/2026 | |
| #14 | add-observability-service | claude-sonnet-4-6 | inject | PASS | 1.00 | Conv5 | 38s | 4/8/2026 | |
| #13 | new-dockerfile | claude-sonnet-4-6 | inject | PASS | 1.00 | Conv5 | 18s | 4/8/2026 | |
| #12 | add-infisical-secret | claude-sonnet-4-6 | inject | PASS | 1.00 | Conv5 | 52s | 4/8/2026 | |
| #11 | fix-application-manifest | claude-sonnet-4-6 | inject | PASS | 1.00 | Conv5 | 36s | 4/8/2026 | |
| #10 | fix-appproject | claude-sonnet-4-6 | inject | PASS | 1.00 | Conv5 | 1m 13s | 4/8/2026 | |
| #9 | add-internal-service | claude-sonnet-4-6 | inject | PASS | 1.00 | Conv5 | 22s | 4/8/2026 | |
| #8 | add-helm-service | claude-sonnet-4-6 | inject | FAIL | 0.94 | Conv4 | 54s | 4/8/2026 | |
| #7 | add-internal-service | claude-sonnet-4-6 | inject | PASS | 1.00 | Corr5 | 22s | 4/8/2026 |