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 | 0.0000 | $26.92 | 100.5M | 603k | 1h 48m | 377 | 5 |
| 2 | Muse Spark 1.2 | 0.0000 | $12.08 | 49.7M | 275k | 1h 6m | 250 | 8 |
| 3 | Muse Spark 1.2 | 0.0000 | $16.11 | 78.5M | 517k | 1h 19m | 309 | 4 |
| 4 | Muse Spark 1.2 | 0.0000 | $13.70 | 75.9M | 319k | 1h 35m | 305 | 3 |
| 5 | Muse Spark 1.2 | 0.0000 | $16.58 | 87.1M | 508k | 2h 14m | 321 | 6 |