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 | 0.1277 | $499.70 | 617.7M | 951k | 19h 17m | 1401 | 24 |
| 2 | Muse Spark 1.3 | 0.1028 | $438.57 | 557.6M | 1.0M | 16h 30m | 1340 | 23 |
| 3 | Muse Spark 1.3 | 0.1003 | $186.76 | 239.3M | 502k | 7h 59m | 559 | 14 |
| 4 | Muse Spark 1.3 | 0.0996 | $157.06 | 200.2M | 465k | 6h 34m | 504 | 12 |
| 5 | Muse Spark 1.3 | 0.0779 | $279.58 | 336.6M | 595k | 9h 26m | 688 | 17 |