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 | 0.1055 | $206.91 | 689.2M | 886k | 10h 35m | 1681 | 1 |
| 2 | Muse Spark 1.3 | 0.0410 | $299.15 | 649.2M | 932k | 19h 37m | 1588 | 2 |
| 3 | Muse Spark 1.3 | 0.0386 | $233.75 | 628.1M | 517k | 18h 2m | 1282 | 5 |
| 4 | Muse Spark 1.3 | 0.0254 | $147.68 | 673.6M | 1.0M | 19h 47m | 1561 | 8 |
| 5 | Muse Spark 1.3 | 0.0250 | $351.72 | 511.0M | 807k | 19h 59m | 1300 | 1 |