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 | 0.8136 | $31.62 | 38.2M | 374k | 3h 49m | 186 | 5 |
| 2 | Muse Spark 1.3 | 0.8036 | $155.17 | 181.2M | 487k | 18h 42m | 545 | 11 |
| 3 | Muse Spark 1.3 | 0.7809 | $183.67 | 203.2M | 648k | 10h 29m | 557 | 11 |
| 4 | Muse Spark 1.3 | 0.6457 | $320.20 | 329.1M | 590k | 13h 47m | 773 | 12 |
| 5 | Muse Spark 1.3 | 0.6302 | $29.92 | 88.8M | 460k | 3h 13m | 325 | 9 |