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 | 0.4228 | $418.71 | 442.8M | 1.1M | 20h 0m | 1119 | 1 |
| 2 | Muse Spark 1.3 | 0.4228 | $514.22 | 583.5M | 1.3M | 19h 59m | 1415 | 1 |
| 3 | Muse Spark 1.3 | 0.3577 | $352.28 | 387.2M | 1.4M | 19h 43m | 1153 | 3 |
| 4 | Muse Spark 1.3 | 0.1463 | $336.34 | 348.3M | 1.1M | 19h 35m | 939 | 9 |
| 5 | Muse Spark 1.3 | 0.0163 | $435.17 | 464.8M | 1.2M | 19h 59m | 1196 | 1 |