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 | 0.9331 | $62.26 | 106.8M | 367k | 8h 14m | 284 | 8 |
| 2 | Claude Fable 5.1 | 0.9314 | $52.87 | 90.3M | 319k | 5h 49m | 274 | 9 |
| 3 | Claude Fable 5.1 | 0.9205 | $68.80 | 118.8M | 390k | 9h 16m | 323 | 6 |
| 4 | Claude Fable 5.1 | 0.9192 | $42.87 | 72.2M | 281k | 5h 13m | 226 | 5 |
| 5 | Claude Fable 5.1 | 0.9186 | $55.53 | 95.2M | 329k | 8h 32m | 279 | 10 |