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 | 0.4569 | $29.57 | 105.7M | 282k | 17h 55m | 519 | 8 |
| 2 | Muse Spark 1.3 | 0.4340 | $126.99 | 121.2M | 301k | 15h 7m | 437 | 9 |
| 3 | Muse Spark 1.3 | 0.4243 | $152.31 | 160.5M | 376k | 14h 14m | 500 | 7 |
| 4 | Muse Spark 1.3 | 0.4206 | $121.45 | 118.8M | 279k | 16h 52m | 510 | 21 |
| 5 | Muse Spark 1.3 | 0.3962 | $92.96 | 91.1M | 258k | 17h 50m | 454 | 10 |