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 | 0.6002 | $67.85 | 117.2M | 379k | 14h 26m | 401 | 17 |
| 2 | Claude Fable 5.1 | 0.5736 | $77.68 | 134.5M | 428k | 13h 49m | 450 | 16 |
| 3 | Claude Fable 5.1 | 0.5457 | $68.00 | 118.2M | 365k | 13h 15m | 419 | 21 |
| 4 | Claude Fable 5.1 | 0.5279 | $64.70 | 113.1M | 334k | 17h 24m | 419 | 17 |
| 5 | Claude Fable 5.1 | 0.4824 | $61.77 | 107.1M | 338k | 15h 49m | 418 | 16 |