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 | 0.4036 | $5.41 | 24.7M | 331k | 4h 44m | 150 | 2 |
| 2 | Muse Spark 1.2 | 0.4036 | $6.73 | 30.6M | 391k | 4h 23m | 132 | 4 |
| 3 | Muse Spark 1.2 | 0.3750 | $11.18 | 57.5M | 431k | 6h 54m | 254 | 6 |
| 4 | Muse Spark 1.2 | 0.3429 | $9.01 | 40.4M | 451k | 7h 47m | 197 | 4 |
| 5 | Muse Spark 1.2 | 0.2071 | $9.69 | 39.5M | 748k | 4h 22m | 138 | 7 |