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 | 1.0000 | $44.19 | 69.8M | 381k | 3h 24m | 215 | 8 |
| 2 | Claude Fable 5.1 | 1.0000 | $51.03 | 82.5M | 402k | 3h 56m | 245 | 12 |
| 3 | Claude Fable 5.1 | 1.0000 | $55.84 | 88.8M | 470k | 3h 14m | 235 | 6 |
| 4 | Claude Fable 5.1 | 0.8463 | $43.78 | 69.0M | 381k | 3h 39m | 231 | 1 |
| 5 | Claude Fable 5.1 | 0.6667 | $57.38 | 92.1M | 466k | 4h 40m | 248 | 7 |