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 | 0.9674 | $40.40 | 26.4M | 189k | 18h 39m | 181 | 7 |
| 2 | Claude Fable 5 | 0.9086 | $35.59 | 21.8M | 190k | 19h 5m | 148 | 4 |
| 3 | Claude Fable 5 | 0.8825 | $22.87 | 13.4M | 129k | 19h 3m | 134 | 6 |
| 4 | Claude Fable 5 | 0.8027 | $24.76 | 14.6M | 137k | 19h 30m | 133 | 7 |
| 5 | Claude Fable 5 | 0.0239 | $24.85 | 14.9M | 135k | 19h 4m | 143 | 7 |