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 | 0.6821 | $28.97 | 85.7M | 430k | 5h 33m | 396 | 21 |
| 2 | Muse Spark 1.3 | 0.6752 | $165.04 | 162.2M | 432k | 18h 15m | 706 | 25 |
| 3 | Muse Spark 1.3 | 0.6538 | $51.51 | 57.6M | 507k | 5h 41m | 286 | 10 |
| 4 | Muse Spark 1.3 | 0.6245 | $65.15 | 69.0M | 497k | 6h 34m | 381 | 13 |
| 5 | Muse Spark 1.3 | 0.6205 | $141.97 | 139.6M | 348k | 19h 5m | 580 | 13 |