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 1.2 | 0.6241 | $2.29 | 11.0M | 77k | 1h 6m | 128 | 3 |
| 2 | Muse Spark 1.2 | 0.1043 | $2.53 | 9.5M | 123k | 1h 21m | 101 | 1 |
| 3 | Muse Spark 1.2 | 0.1040 | $2.18 | 10.0M | 104k | 1h 4m | 113 | 2 |
| 4 | Muse Spark 1.2 | 0.1040 | $3.41 | 16.0M | 109k | 59m | 110 | 2 |
| 5 | Muse Spark 1.2 | 0.0377 | $5.55 | 30.5M | 146k | 1h 16m | 174 | 2 |