Every run: the agent's full trajectory, its submissions over the 20-hour budget, and the final score.
| # | Model | Reward | Cost | In tok | Out tok | Time | Steps | Submits |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 0.3604 | $65.32 | 119.8M | 246k | 14h 32m | 399 | 16 |
| 2 | Claude Fable 5.1 | 0.3524 | $77.13 | 147.0M | 311k | 14h 51m | 472 | 5 |
| 3 | Claude Fable 5.1 | 0.2715 | $77.56 | 137.7M | 370k | 10h 32m | 426 | 7 |
| 4 | Claude Fable 5.1 | 0.2491 | $104.18 | 191.5M | 350k | 15h 56m | 562 | 8 |
| 5 | Claude Fable 5.1 | 0.1812 | $69.87 | 126.5M | 304k | 15h 13m | 418 | 9 |