Every real run, newest first unless a column says otherwise. Open one to see the page the agent wrote, its violations and what each step cost.
Only runs of rule raw-values/raw-number (remove).
| Task | Model | Context | Design system | Quality | Done | Steps | Cost | When ↑ |
|---|---|---|---|---|---|---|---|---|
| loan-contract | deepseek-v4.1-flash-1017 | none | 145 | 24 | Done | 5 | $0.0184 |
3 runs match.
| Nov 9, 09:01 |
| statement | deepseek-v4.1-flash-1017 | none | 124 | 16 | Done | 7 | $0.0308 | Nov 9, 09:03 |
| transfer-form | deepseek-v4.1-flash-1017 | none | 60 | 7 | Incomplete | 5 | $0.0124 | Nov 9, 09:05 |