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 | 0.5582 | $533.21 | 614.5M | 1.1M | 19h 59m | 1577 | 1 |
| 2 | Muse Spark 1.3 | 0.5497 | $512.38 | 619.2M | 1.1M | 19h 59m | 1598 | 1 |
| 3 | Muse Spark 1.3 | 0.4932 | $275.58 | 1496.0M | 1.9M | 19h 49m | 3361 | 3 |
| 4 | Muse Spark 1.3 | 0.4932 | $515.26 | 603.1M | 1.3M | 19h 58m | 1473 | 2 |
| 5 | Muse Spark 1.3 | 0.4384 | $522.03 | 583.4M | 1.2M | 19h 58m | 1409 | 1 |