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 | Muse Spark 1.2 | 0.1646 | $89.68 | 227.7M | 1.2M | 20h 2m | 728 | 7 |
| 2 | Muse Spark 1.2 | 0.1353 | $32.24 | 170.7M | 487k | 10h 37m | 551 | 5 |
| 3 | Muse Spark 1.2 | 0.0816 | $32.40 | 192.3M | 534k | 7h 46m | 570 | 4 |
| 4 | Muse Spark 1.2 | 0.0387 | $183.05 | 621.0M | 1.3M | 19h 7m | 1497 | 7 |
| 5 | Muse Spark 1.2 | 0.0356 | $37.95 | 196.7M | 1.2M | 19h 2m | 669 | 3 |