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 | 0.5758 | $268.72 | 1376.2M | 2.2M | 19h 51m | 3328 | 2 |
| 2 | Muse Spark 1.3 | 0.5657 | $460.65 | 531.6M | 1.1M | 17h 48m | 1347 | 4 |
| 3 | Muse Spark 1.3 | 0.5455 | $559.10 | 664.1M | 1.1M | 19h 47m | 1540 | 5 |
| 4 | Muse Spark 1.3 | 0.4646 | $547.17 | 608.4M | 1.3M | 19h 44m | 1331 | 3 |
| 5 | Muse Spark 1.3 | 0.3939 | $557.80 | 621.9M | 1.5M | 19h 58m | 1391 | 1 |