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 | 0.8953 | $64.06 | 109.1M | 391k | 4h 49m | 305 | 17 |
| 2 | Claude Fable 5.1 | 0.8935 | $57.22 | 97.5M | 350k | 6h 25m | 298 | 24 |
| 3 | Claude Fable 5.1 | 0.8000 | $36.76 | 59.7M | 285k | 3h 53m | 220 | 11 |
| 4 | Claude Fable 5.1 | 0.7999 | $32.01 | 51.0M | 267k | 3h 57m | 202 | 12 |
| 5 | Claude Fable 5.1 | 0.7955 | $42.10 | 68.8M | 317k | 4h 11m | 232 | 12 |