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 | 0.2056 | $84.96 | 112.8M | 364k | 5h 13m | 428 | 19 |
| 2 | Muse Spark 1.3 | 0.1015 | $57.05 | 70.7M | 278k | 5h 16m | 361 | 11 |
| 3 | Muse Spark 1.3 | 0.0976 | $81.13 | 81.9M | 258k | 12h 38m | 397 | 2 |
| 4 | Muse Spark 1.3 | 0.0279 | $94.74 | 98.7M | 274k | 19h 49m | 426 | 38 |
| 5 | Muse Spark 1.3 | 0.0028 | $18.89 | 27.3M | 239k | 2h 57m | 175 | 4 |