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 | 0.9041 | $8.87 | 38.4M | 436k | 2h 57m | 150 | 1 |
| 2 | Muse Spark 1.2 | 0.7187 | $4.40 | 15.5M | 216k | 1h 29m | 110 | 2 |
| 3 | Muse Spark 1.2 | 0.7132 | $3.96 | 18.1M | 225k | 49m | 126 | 4 |
| 4 | Muse Spark 1.2 | 0.1494 | $13.10 | 65.0M | 597k | 2h 52m | 267 | 1 |
| 5 | Muse Spark 1.2 | 0.0498 | $2.47 | 8.0M | 164k | 1h 0m | 83 | 2 |