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 | 0.2857 | $5.65 | 7.6M | 75k | 17h 4m | 98 | 2 |
| 2 | Claude Fable 5.1 | 0.2857 | $5.38 | 7.9M | 60k | 16h 16m | 118 | 3 |
| 3 | Claude Fable 5.1 | 0.2619 | $6.12 | 8.6M | 75k | 18h 44m | 112 | 4 |
| 4 | Claude Fable 5.1 | 0.2143 | $5.26 | 7.1M | 71k | 18h 19m | 92 | 3 |
| 5 | Claude Fable 5.1 | 0.1667 | $6.92 | 9.6M | 88k | 17h 1m | 101 | 4 |