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 | 0.5524 | $214.49 | 1195.2M | 2.0M | 12h 19m | 2846 | 1 |
| 2 | Muse Spark 1.3 | 0.3727 | $330.62 | 1484.1M | 2.3M | 19h 59m | 3305 | 30 |
| 3 | Muse Spark 1.3 | 0.3146 | $507.64 | 559.8M | 1.1M | 19h 23m | 1354 | 2 |
| 4 | Muse Spark 1.3 | 0.0797 | $528.52 | 575.6M | 1.2M | 19h 59m | 1313 | 1 |
| 5 | Muse Spark 1.3 | 0.0480 | $556.48 | 567.3M | 735k | 19h 51m | 1107 | 5 |