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 1.3 | 0.9776 | $411.77 | 410.4M | 713k | 19h 52m | 799 | 2 |
| 2 | Muse Spark 1.3 | 0.7421 | $154.98 | 818.9M | 1.3M | 19h 49m | 1805 | 2 |
| 3 | Muse Spark 1.3 | 0.5609 | $411.55 | 416.2M | 856k | 19h 58m | 959 | 1 |
| 4 | Muse Spark 1.3 | 0.5029 | $384.24 | 384.5M | 940k | 19h 50m | 937 | 1 |
| 5 | Muse Spark 1.3 | 0.3530 | $389.61 | 408.6M | 860k | 19h 59m | 1015 | 1 |