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 | 0.1313 | $32.05 | 183.6M | 731k | 2h 8m | 465 | 1 |
| 2 | Muse Spark 1.2 | 0.0707 | $10.81 | 53.3M | 351k | 1h 35m | 223 | 2 |
| 3 | Muse Spark 1.2 | 0.0707 | $32.82 | 175.7M | 815k | 3h 21m | 461 | 1 |
| 4 | Muse Spark 1.2 | 0.0505 | $8.77 | 48.8M | 242k | 1h 16m | 196 | 2 |
| 5 | Muse Spark 1.2 | 0.0404 | $5.34 | 27.9M | 188k | 26m | 143 | 2 |