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 | 0.0055 | $37.82 | 217.7M | 976k | 3h 48m | 496 | 10 |
| 2 | Muse Spark 1.2 | 0.0055 | $40.72 | 146.5M | 561k | 3h 14m | 420 | 4 |
| 3 | Muse Spark 1.2 | 0.0000 | $32.40 | 176.5M | 473k | 2h 53m | 436 | 3 |
| 4 | Muse Spark 1.2 | 0.0000 | $14.08 | 83.6M | 240k | 1h 8m | 314 | 2 |
| 5 | Muse Spark 1.2 | 0.0000 | $33.19 | 162.4M | 603k | 2h 4m | 458 | 1 |