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 | 0.3826 | $317.27 | 411.4M | 767k | 19h 50m | 1032 | 4 |
| 2 | Muse Spark 1.3 | 0.3439 | $236.90 | 672.0M | 957k | 19h 49m | 1569 | 5 |
| 3 | Muse Spark 1.3 | 0.0370 | $445.62 | 445.7M | 615k | 19h 19m | 857 | 8 |
| 4 | Muse Spark 1.3 | 0.0000 | $518.18 | 574.1M | 1.1M | 19h 44m | 1290 | 6 |
| 5 | Muse Spark 1.3 | 0.0000 | $449.88 | 491.2M | 832k | 19h 52m | 1176 | 2 |