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 | 0.3456 | $4.38 | 18.4M | 145k | 37m | 104 | 2 |
| 2 | Muse Spark 1.2 | 0.3227 | $38.37 | 235.4M | 385k | 2h 26m | 592 | 5 |
| 3 | Muse Spark 1.2 | 0.3018 | $11.62 | 45.2M | 202k | 1h 9m | 181 | 7 |
| 4 | Muse Spark 1.2 | 0.2944 | $2.12 | 8.7M | 99k | 50m | 86 | 1 |
| 5 | Muse Spark 1.2 | 0.2758 | $11.17 | 51.5M | 378k | 2h 40m | 211 | 6 |