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 | 0.9332 | $262.30 | 478.6M | 947k | 9h 23m | 1148 | 17 |
| 2 | Claude Fable 5.1 | 0.9315 | $216.99 | 391.4M | 878k | 7h 55m | 966 | 6 |
| 3 | Claude Fable 5.1 | 0.9195 | $211.66 | 382.5M | 840k | 9h 40m | 989 | 17 |
| 4 | Claude Fable 5.1 | 0.9161 | $266.36 | 483.7M | 1.0M | 10h 14m | 1167 | 34 |
| 5 | Claude Fable 5.1 | 0.9092 | $168.96 | 308.4M | 606k | 6h 47m | 586 | 10 |