Recent runs and prior experiments
Runs are shown contextually here instead of being a primary destination.
| Environment | Prompt | Model | Result | Timestamp |
|---|---|---|---|---|
| Snake challenge | Safety-first v3 | gpt-4.1-mini | Score 902 | 2026-03-12 14:21 |
| Snake challenge | Format Guard v2 | gpt-4o-mini | Score 844 | 2026-03-12 13:02 |
| Grid challenge | Constraint Path v1 | gpt-4.1 | Score 931 | 2026-03-11 19:48 |