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 | 0.3484 | $166.03 | 303.2M | 604k | 16h 29m | 825 | 13 |
| 2 | Claude Fable 5.1 | 0.3356 | $233.87 | 425.4M | 876k | 16h 37m | 1021 | 18 |
| 3 | Claude Fable 5.1 | 0.2852 | $199.91 | 365.0M | 723k | 15h 17m | 974 | 15 |
| 4 | Claude Fable 5.1 | 0.2009 | $170.71 | 311.4M | 625k | 17h 11m | 813 | 17 |
| 5 | Claude Fable 5.1 | 0.0000 | $232.11 | 427.5M | 765k | 16h 0m | 1023 | 35 |